Daily Papers

Credit and risk assessments are cornerstones of the financial landscape, impacting both individual futures and broader societal constructs. Existing credit scoring models often exhibit limitations stemming from knowledge myopia and task isolation. In response, we formulate three hypotheses and undertake an extensive case study to investigate LLMs' viability in credit assessment. Our empirical investigations unveil LLMs' ability to overcome the limitations inherent in conventional models. We introduce a novel benchmark curated for credit assessment purposes, fine-tune a specialized Credit and Risk Assessment Large Language Model (CALM), and rigorously examine the biases that LLMs may harbor. Our findings underscore LLMs' potential in revolutionizing credit assessment, showcasing their adaptability across diverse financial evaluations, and emphasizing the critical importance of impartial decision-making in the financial sector. Our datasets, models, and benchmarks are open-sourced for other researchers.

We introduce Atla Selene Mini, a state-of-the-art small language model-as-a-judge (SLMJ). Selene Mini is a general-purpose evaluator that outperforms the best SLMJs and GPT-4o-mini on overall performance across 11 out-of-distribution benchmarks, spanning absolute scoring, classification, and pairwise preference tasks. It is the highest-scoring 8B generative model on RewardBench, surpassing strong baselines like GPT-4o and specialized judges. To achieve this, we develop a principled data curation strategy that augments public datasets with synthetically generated critiques and ensures high quality through filtering and dataset ablations. We train our model on a combined direct preference optimization (DPO) and supervised fine-tuning (SFT) loss, and produce a highly promptable evaluator that excels in real-world scenarios. Selene Mini shows dramatically improved zero-shot agreement with human expert evaluations on financial and medical industry datasets. It is also robust to variations in prompt format. Preliminary results indicate that Selene Mini is the top-ranking evaluator in a live, community-driven Judge Arena. We release the model weights on HuggingFace (https://hf.co/AtlaAI/Selene-1-Mini-Llama-3.1-8B) and Ollama to encourage widespread community adoption.

Financial markets are complex systems characterized by high statistical noise, nonlinearity, and constant evolution. Thus, modeling them is extremely hard. We address the task of generating realistic and responsive Limit Order Book (LOB) market simulations, which are fundamental for calibrating and testing trading strategies, performing market impact experiments, and generating synthetic market data. Previous works lack realism, usefulness, and responsiveness of the generated simulations. To bridge this gap, we propose a novel TRAnsformer-based Denoising Diffusion Probabilistic Engine for LOB Simulations (TRADES). TRADES generates realistic order flows conditioned on the state of the market, leveraging a transformer-based architecture that captures the temporal and spatial characteristics of high-frequency market data. There is a notable absence of quantitative metrics for evaluating generative market simulation models in the literature. To tackle this problem, we adapt the predictive score, a metric measured as an MAE, by training a stock price predictive model on synthetic data and testing it on real data. We compare TRADES with previous works on two stocks, reporting an x3.27 and x3.47 improvement over SoTA according to the predictive score, demonstrating that we generate useful synthetic market data for financial downstream tasks. We assess TRADES's market simulation realism and responsiveness, showing that it effectively learns the conditional data distribution and successfully reacts to an experimental agent, giving sprout to possible calibrations and evaluations of trading strategies and market impact experiments. We developed DeepMarket, the first open-source Python framework for market simulation with deep learning. Our repository includes a synthetic LOB dataset composed of TRADES's generates simulations. We release the code at github.com/LeonardoBerti00/DeepMarket.

The financial domain poses unique challenges for knowledge graph (KG) construction at scale due to the complexity and regulatory nature of financial documents. Despite the critical importance of structured financial knowledge, the field lacks large-scale, open-source datasets capturing rich semantic relationships from corporate disclosures. We introduce an open-source, large-scale financial knowledge graph dataset built from the latest annual SEC 10-K filings of all S and P 100 companies - a comprehensive resource designed to catalyze research in financial AI. We propose a robust and generalizable knowledge graph (KG) construction framework that integrates intelligent document parsing, table-aware chunking, and schema-guided iterative extraction with a reflection-driven feedback loop. Our system incorporates a comprehensive evaluation pipeline, combining rule-based checks, statistical validation, and LLM-as-a-Judge assessments to holistically measure extraction quality. We support three extraction modes - single-pass, multi-pass, and reflection-agent-based - allowing flexible trade-offs between efficiency, accuracy, and reliability based on user requirements. Empirical evaluations demonstrate that the reflection-agent-based mode consistently achieves the best balance, attaining a 64.8 percent compliance score against all rule-based policies (CheckRules) and outperforming baseline methods (single-pass and multi-pass) across key metrics such as precision, comprehensiveness, and relevance in LLM-guided evaluations.

Retrieval-Augmented Generation (RAG) has emerged as a promising framework to mitigate hallucinations in Large Language Models (LLMs), yet its overall performance is dependent on the underlying retrieval system. In the finance domain, documents such as 10-K reports pose distinct challenges due to domain-specific vocabulary and multi-hierarchical tabular data. In this work, we introduce an efficient, end-to-end RAG pipeline that enhances retrieval for financial documents through a three-phase approach: pre-retrieval, retrieval, and post-retrieval. In the pre-retrieval phase, various query and corpus preprocessing techniques are employed to enrich input data. During the retrieval phase, we fine-tuned state-of-the-art (SOTA) embedding models with domain-specific knowledge and implemented a hybrid retrieval strategy that combines dense and sparse representations. Finally, the post-retrieval phase leverages Direct Preference Optimization (DPO) training and document selection methods to further refine the results. Evaluations on seven financial question answering datasets-FinDER, FinQABench, FinanceBench, TATQA, FinQA, ConvFinQA, and MultiHiertt-demonstrate substantial improvements in retrieval performance, leading to more accurate and contextually appropriate generation. These findings highlight the critical role of tailored retrieval techniques in advancing the effectiveness of RAG systems for financial applications. A fully replicable pipeline is available on GitHub: https://github.com/seohyunwoo-0407/GAR.

We propose Multiple Experts Fine-tuning Framework to build a financial large language model (LLM), DISC-FinLLM. Our methodology improves general LLMs by endowing them with multi-turn question answering abilities, domain text processing capabilities, mathematical computation skills, and retrieval-enhanced generation capabilities. We build a financial instruction-tuning dataset named DISC-FIN-SFT, including instruction samples of four categories (consulting, NLP tasks, computing and retrieval-augmented generation). Evaluations conducted on multiple benchmarks demonstrate that our model performs better than baseline models in various financial scenarios. Further resources can be found at https://github.com/FudanDISC/DISC-FinLLM.

Large language models (LLMs) have advanced financial applications, yet they often lack sufficient financial knowledge and struggle with tasks involving multi-modal inputs like tables and time series data. To address these limitations, we introduce Open-FinLLMs, a series of Financial LLMs. We begin with FinLLaMA, pre-trained on a 52 billion token financial corpus, incorporating text, tables, and time-series data to embed comprehensive financial knowledge. FinLLaMA is then instruction fine-tuned with 573K financial instructions, resulting in FinLLaMA-instruct, which enhances task performance. Finally, we present FinLLaVA, a multimodal LLM trained with 1.43M image-text instructions to handle complex financial data types. Extensive evaluations demonstrate FinLLaMA's superior performance over LLaMA3-8B, LLaMA3.1-8B, and BloombergGPT in both zero-shot and few-shot settings across 19 and 4 datasets, respectively. FinLLaMA-instruct outperforms GPT-4 and other Financial LLMs on 15 datasets. FinLLaVA excels in understanding tables and charts across 4 multimodal tasks. Additionally, FinLLaMA achieves impressive Sharpe Ratios in trading simulations, highlighting its robust financial application capabilities. We will continually maintain and improve our models and benchmarks to support ongoing innovation in academia and industry.

In recent years, large language models (LLMs) have demonstrated significant potential in constructing passage retrieval datasets. However, existing methods still face limitations in expressing cross-doc query needs and controlling annotation quality. To address these issues, this paper proposes a bidirectional generation pipeline, which aims to generate 3-level hierarchical queries for both intra-doc and cross-doc scenarios and mine additional relevance labels on top of direct mapping annotation. The pipeline introduces two query generation methods: bottom-up from single-doc text and top-down from multi-doc titles. The bottom-up method uses LLMs to disassemble and generate structured queries at both sentence-level and passage-level simultaneously from intra-doc passages. The top-down approach incorporates three key financial elements--industry, topic, and time--to divide report titles into clusters and prompts LLMs to generate topic-level queries from each cluster. For relevance annotation, our pipeline not only relies on direct mapping annotation from the generation relationship but also implements an indirect positives mining method to enrich the relevant query-passage pairs. Using this pipeline, we constructed a Financial Passage Retrieval Generated dataset (FinCPRG) from almost 1.3k Chinese financial research reports, which includes hierarchical queries and rich relevance labels. Through evaluations of mined relevance labels, benchmarking and training experiments, we assessed the quality of FinCPRG and validated its effectiveness as a passage retrieval dataset for both training and benchmarking.

In this work, we present the first open leaderboard for evaluating Korean large language models focused on finance. Operated for about eight weeks, the leaderboard evaluated 1,119 submissions on a closed benchmark covering five MCQA categories: finance and accounting, stock price prediction, domestic company analysis, financial markets, and financial agent tasks and one open-ended qa task. Building on insights from these evaluations, we release an open instruction dataset of 80k instances and summarize widely used training strategies observed among top-performing models. Finally, we introduce Won, a fully open and transparent LLM built using these best practices. We hope our contributions help advance the development of better and safer financial LLMs for Korean and other languages.

The emergence of Large Language Models (LLMs), such as ChatGPT, has revolutionized general natural language preprocessing (NLP) tasks. However, their expertise in the financial domain lacks a comprehensive evaluation. To assess the ability of LLMs to solve financial NLP tasks, we present FinLMEval, a framework for Financial Language Model Evaluation, comprising nine datasets designed to evaluate the performance of language models. This study compares the performance of encoder-only language models and the decoder-only language models. Our findings reveal that while some decoder-only LLMs demonstrate notable performance across most financial tasks via zero-shot prompting, they generally lag behind the fine-tuned expert models, especially when dealing with proprietary datasets. We hope this study provides foundation evaluations for continuing efforts to build more advanced LLMs in the financial domain.

This paper introduces the UCFE: User-Centric Financial Expertise benchmark, an innovative framework designed to evaluate the ability of large language models (LLMs) to handle complex real-world financial tasks. UCFE benchmark adopts a hybrid approach that combines human expert evaluations with dynamic, task-specific interactions to simulate the complexities of evolving financial scenarios. Firstly, we conducted a user study involving 804 participants, collecting their feedback on financial tasks. Secondly, based on this feedback, we created our dataset that encompasses a wide range of user intents and interactions. This dataset serves as the foundation for benchmarking 12 LLM services using the LLM-as-Judge methodology. Our results show a significant alignment between benchmark scores and human preferences, with a Pearson correlation coefficient of 0.78, confirming the effectiveness of the UCFE dataset and our evaluation approach. UCFE benchmark not only reveals the potential of LLMs in the financial sector but also provides a robust framework for assessing their performance and user satisfaction.The benchmark dataset and evaluation code are available.

Large Language Models (LLMs) have recently been leveraged for asset pricing tasks and stock trading applications, enabling AI agents to generate investment decisions from unstructured financial data. However, most evaluations of LLM timing-based investing strategies are conducted on narrow timeframes and limited stock universes, overstating effectiveness due to survivorship and data-snooping biases. We critically assess their generalizability and robustness by proposing FINSABER, a backtesting framework evaluating timing-based strategies across longer periods and a larger universe of symbols. Systematic backtests over two decades and 100+ symbols reveal that previously reported LLM advantages deteriorate significantly under broader cross-section and over a longer-term evaluation. Our market regime analysis further demonstrates that LLM strategies are overly conservative in bull markets, underperforming passive benchmarks, and overly aggressive in bear markets, incurring heavy losses. These findings highlight the need to develop LLM strategies that are able to prioritise trend detection and regime-aware risk controls over mere scaling of framework complexity.

In this research paper, we investigate into a paper named "A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problem" [arXiv:1706.10059]. It is a portfolio management problem which is solved by deep learning techniques. The original paper proposes a financial-model-free reinforcement learning framework, which consists of the Ensemble of Identical Independent Evaluators (EIIE) topology, a Portfolio-Vector Memory (PVM), an Online Stochastic Batch Learning (OSBL) scheme, and a fully exploiting and explicit reward function. Three different instants are used to realize this framework, namely a Convolutional Neural Network (CNN), a basic Recurrent Neural Network (RNN), and a Long Short-Term Memory (LSTM). The performance is then examined by comparing to a number of recently reviewed or published portfolio-selection strategies. We have successfully replicated their implementations and evaluations. Besides, we further apply this framework in the stock market, instead of the cryptocurrency market that the original paper uses. The experiment in the cryptocurrency market is consistent with the original paper, which achieve superior returns. But it doesn't perform as well when applied in the stock market.

The introduction of ISO 12913-2:2018 has provided a framework for standardized data collection and reporting procedures for soundscape practitioners. A strong emphasis was placed on the use of calibrated head and torso simulators (HATS) for binaural audio capture to obtain an accurate subjective impression and acoustic measure of the soundscape under evaluation. To auralise the binaural recordings as recorded or at set levels, the audio stimuli and the headphone setup are usually calibrated with a HATS. However, calibrated HATS are too financially prohibitive for most research teams, inevitably diminishing the availability of the soundscape standard. With the increasing availability of soundscape binaural recording datasets, and the importance of cross-cultural validation of the soundscape ISO standards, e.g.\ via the Soundscape Attributes Translation Project (SATP), it is imperative to assess the suitability of cost-effective headphone calibration methods to maximise availability without severely compromising on accuracy. Hence, this study objectively examines an open-circuit voltage (OCV) calibration method in comparison to a calibrated HATS on various soundcard and headphone combinations. Preliminary experiments found that calibration with the OCV method differed significantly from the reference binaural recordings in sound pressure levels, whereas negligible differences in levels were observed with the HATS calibration.

LLMs have transformed NLP and shown promise in various fields, yet their potential in finance is underexplored due to a lack of thorough evaluations and the complexity of financial tasks. This along with the rapid development of LLMs, highlights the urgent need for a systematic financial evaluation benchmark for LLMs. In this paper, we introduce FinBen, the first comprehensive open-sourced evaluation benchmark, specifically designed to thoroughly assess the capabilities of LLMs in the financial domain. FinBen encompasses 35 datasets across 23 financial tasks, organized into three spectrums of difficulty inspired by the Cattell-Horn-Carroll theory, to evaluate LLMs' cognitive abilities in inductive reasoning, associative memory, quantitative reasoning, crystallized intelligence, and more. Our evaluation of 15 representative LLMs, including GPT-4, ChatGPT, and the latest Gemini, reveals insights into their strengths and limitations within the financial domain. The findings indicate that GPT-4 leads in quantification, extraction, numerical reasoning, and stock trading, while Gemini shines in generation and forecasting; however, both struggle with complex extraction and forecasting, showing a clear need for targeted enhancements. Instruction tuning boosts simple task performance but falls short in improving complex reasoning and forecasting abilities. FinBen seeks to continuously evaluate LLMs in finance, fostering AI development with regular updates of tasks and models.

This paper proposes PyFi, a novel framework for pyramid-like financial image understanding that enables vision language models (VLMs) to reason through question chains in a progressive, simple-to-complex manner. At the core of PyFi is PyFi-600K, a dataset comprising 600K financial question-answer pairs organized into a reasoning pyramid: questions at the base require only basic perception, while those toward the apex demand increasing levels of capability in financial visual understanding and expertise. This data is scalable because it is synthesized without human annotations, using PyFi-adv, a multi-agent adversarial mechanism under the Monte Carlo Tree Search (MCTS) paradigm, in which, for each image, a challenger agent competes with a solver agent by generating question chains that progressively probe deeper capability levels in financial visual reasoning. Leveraging this dataset, we present fine-grained, hierarchical, and comprehensive evaluations of advanced VLMs in the financial domain. Moreover, fine-tuning Qwen2.5-VL-3B and Qwen2.5-VL-7B on the pyramid-structured question chains enables these models to answer complex financial questions by decomposing them into sub-questions with gradually increasing reasoning demands, yielding average accuracy improvements of 19.52% and 8.06%, respectively, on the dataset. All resources of code, dataset and models are available at: https://github.com/AgenticFinLab/PyFi .

We introduce SECQUE, a comprehensive benchmark for evaluating large language models (LLMs) in financial analysis tasks. SECQUE comprises 565 expert-written questions covering SEC filings analysis across four key categories: comparison analysis, ratio calculation, risk assessment, and financial insight generation. To assess model performance, we develop SECQUE-Judge, an evaluation mechanism leveraging multiple LLM-based judges, which demonstrates strong alignment with human evaluations. Additionally, we provide an extensive analysis of various models' performance on our benchmark. By making SECQUE publicly available, we aim to facilitate further research and advancements in financial AI.

As a typical and practical application of Large Language Models (LLMs), Retrieval-Augmented Generation (RAG) techniques have gained extensive attention, particularly in vertical domains where LLMs may lack domain-specific knowledge. In this paper, we introduce an omnidirectional and automatic RAG benchmark, OmniEval, in the financial domain. Our benchmark is characterized by its multi-dimensional evaluation framework, including (1) a matrix-based RAG scenario evaluation system that categorizes queries into five task classes and 16 financial topics, leading to a structured assessment of diverse query scenarios; (2) a multi-dimensional evaluation data generation approach, which combines GPT-4-based automatic generation and human annotation, achieving an 87.47\% acceptance ratio in human evaluations on generated instances; (3) a multi-stage evaluation system that evaluates both retrieval and generation performance, result in a comprehensive evaluation on the RAG pipeline; and (4) robust evaluation metrics derived from rule-based and LLM-based ones, enhancing the reliability of assessments through manual annotations and supervised fine-tuning of an LLM evaluator. Our experiments demonstrate the comprehensiveness of OmniEval, which includes extensive test datasets and highlights the performance variations of RAG systems across diverse topics and tasks, revealing significant opportunities for RAG models to improve their capabilities in vertical domains. We open source the code of our benchmark in https://github.com/RUC-NLPIR/OmniEval{https://github.com/RUC-NLPIR/OmniEval}.

Foundation models are increasingly central to high-stakes AI systems, and governance frameworks now depend on evaluations to assess their risks and capabilities. Although general capability evaluations are widespread, social impact assessments covering bias, fairness, privacy, environmental costs, and labor practices remain uneven across the AI ecosystem. To characterize this landscape, we conduct the first comprehensive analysis of both first-party and third-party social impact evaluation reporting across a wide range of model developers. Our study examines 186 first-party release reports and 183 post-release evaluation sources, and complements this quantitative analysis with interviews of model developers. We find a clear division of evaluation labor: first-party reporting is sparse, often superficial, and has declined over time in key areas such as environmental impact and bias, while third-party evaluators including academic researchers, nonprofits, and independent organizations provide broader and more rigorous coverage of bias, harmful content, and performance disparities. However, this complementarity has limits. Only model developers can authoritatively report on data provenance, content moderation labor, financial costs, and training infrastructure, yet interviews reveal that these disclosures are often deprioritized unless tied to product adoption or regulatory compliance. Our findings indicate that current evaluation practices leave major gaps in assessing AI's societal impacts, highlighting the urgent need for policies that promote developer transparency, strengthen independent evaluation ecosystems, and create shared infrastructure to aggregate and compare third-party evaluations in a consistent and accessible way.

Recent advancements in Large Language Models (LLMs) and the introduction of the Model Context Protocol (MCP) have significantly expanded LLM agents' capability to interact dynamically with external tools and APIs. However, existing tool selection frameworks do not integrate MCP servers, instead relying heavily on error-prone manual updates to monolithic local tool repositories, leading to duplication, inconsistencies, and inefficiencies. Additionally, current approaches abstract tool selection before the LLM agent is invoked, limiting its autonomy and hindering dynamic re-querying capabilities during multi-turn interactions. To address these issues, we introduce ScaleMCP, a novel tool selection approach that dynamically equips LLM agents with a MCP tool retriever, giving agents the autonomy to add tools into their memory, as well as an auto-synchronizing tool storage system pipeline through CRUD (create, read, update, delete) operations with MCP servers as the single source of truth. We also propose a novel embedding strategy, Tool Document Weighted Average (TDWA), designed to selectively emphasize critical components of tool documents (e.g. tool name or synthetic questions) during the embedding process. Comprehensive evaluations conducted on a created dataset of 5,000 financial metric MCP servers, across 10 LLM models, 5 embedding models, and 5 retriever types, demonstrate substantial improvements in tool retrieval and agent invocation performance, emphasizing ScaleMCP's effectiveness in scalable, dynamic tool selection and invocation.

Recent advances in Large Language Models (LLMs) have demonstrated impressive capabilities in financial reasoning and market understanding. Multi-agent LLM frameworks such as TradingAgent and FINMEM augment these models to long-horizon investment tasks, leveraging fundamental and sentiment-based inputs for strategic decision-making. However, such systems are ill-suited for the high-speed, precision-critical demands of High-Frequency Trading (HFT). HFT requires rapid, risk-aware decisions based on structured, short-horizon signals, including technical indicators, chart patterns, and trend-based features, distinct from the long-term semantic reasoning typical of traditional financial LLM applications. To this end, we introduce QuantAgent, the first multi-agent LLM framework explicitly designed for high-frequency algorithmic trading. The system decomposes trading into four specialized agents, Indicator, Pattern, Trend, and Risk, each equipped with domain-specific tools and structured reasoning capabilities to capture distinct aspects of market dynamics over short temporal windows. In zero-shot evaluations across ten financial instruments, including Bitcoin and Nasdaq futures, QuantAgent demonstrates superior performance in both predictive accuracy and cumulative return over 4-hour trading intervals, outperforming strong neural and rule-based baselines. Our findings suggest that combining structured financial priors with language-native reasoning unlocks new potential for traceable, real-time decision systems in high-frequency financial markets.

Multi-task learning (MTL) has been successfully used in many real-world applications, which aims to simultaneously solve multiple tasks with a single model. The general idea of multi-task learning is designing kinds of global parameter sharing mechanism and task-specific feature extractor to improve the performance of all tasks. However, challenge still remains in balancing the trade-off of various tasks since model performance is sensitive to the relationships between them. Less correlated or even conflict tasks will deteriorate the performance by introducing unhelpful or negative information. Therefore, it is important to efficiently exploit and learn fine-grained feature representation corresponding to each task. In this paper, we propose an Adaptive Pattern Extraction Multi-task (APEM) framework, which is adaptive and flexible for large-scale industrial application. APEM is able to fully utilize the feature information by learning the interactions between the input feature fields and extracted corresponding tasks-specific information. We first introduce a DeepAuto Group Transformer module to automatically and efficiently enhance the feature expressivity with a modified set attention mechanism and a Squeeze-and-Excitation operation. Second, explicit Pattern Selector is introduced to further enable selectively feature representation learning by adaptive task-indicator vectors. Empirical evaluations show that APEM outperforms the state-of-the-art MTL methods on public and real-world financial services datasets. More importantly, we explore the online performance of APEM in a real industrial-level recommendation scenario.

Language models have shown promising performance on the task of translating natural language questions into SQL queries (Text-to-SQL). However, most of the state-of-the-art (SOTA) approaches rely on powerful yet closed-source large language models (LLMs), such as ChatGPT and GPT-4, which may have the limitations of unclear model architectures, data privacy risks, and expensive inference overheads. To address the limitations, we introduce CodeS, a series of pre-trained language models with parameters ranging from 1B to 15B, specifically designed for the text-to-SQL task. CodeS is a fully open-source language model, which achieves superior accuracy with much smaller parameter sizes. This paper studies the research challenges in building CodeS. To enhance the SQL generation abilities of CodeS, we adopt an incremental pre-training approach using a specifically curated SQL-centric corpus. Based on this, we address the challenges of schema linking and rapid domain adaptation through strategic prompt construction and a bi-directional data augmentation technique. We conduct comprehensive evaluations on multiple datasets, including the widely used Spider benchmark, the newly released BIRD benchmark, robustness-diagnostic benchmarks such as Spider-DK, Spider-Syn, Spider-Realistic, and Dr.Spider, as well as two real-world datasets created for financial and academic applications. The experimental results show that our CodeS achieves new SOTA accuracy and robustness on nearly all challenging text-to-SQL benchmarks.

The rapid integration of agentic AI into high-stakes real-world applications requires robust oversight mechanisms. The emerging field of AI Control (AIC) aims to provide such an oversight mechanism, but practical adoption depends heavily on implementation overhead. To study this problem better, we introduce the notion of Control tax -- the operational and financial cost of integrating control measures into AI pipelines. Our work makes three key contributions to the field of AIC: (1) we introduce a theoretical framework that quantifies the Control Tax and maps classifier performance to safety assurances; (2) we conduct comprehensive evaluations of state-of-the-art language models in adversarial settings, where attacker models insert subtle backdoors into code while monitoring models attempt to detect these vulnerabilities; and (3) we provide empirical financial cost estimates for control protocols and develop optimized monitoring strategies that balance safety and cost-effectiveness while accounting for practical constraints like auditing budgets. Our framework enables practitioners to make informed decisions by systematically connecting safety guarantees with their costs, advancing AIC through principled economic feasibility assessment across different deployment contexts.

This paper presents FinGEITje, the first Dutch financial Large Language Model (LLM) specifically designed and optimized for various financial tasks. Together with the model, we release a specialized Dutch financial instruction tuning dataset with over 140,000 samples, constructed employing an automated translation and data processing method. The open-source data construction method is provided, facilitating the creation of financial instruction datasets in different languages. To evaluate model performance, the study introduces the first Dutch financial evaluation benchmark, along with an automated evaluation method that utilizes an LLM as an independent evaluator, reducing manual intervention in performance evaluation. The experimental results highlight the superior performance of FinGEITje across five critical Dutch and English financial tasks.

Large Language Models (LLMs) have shown promise for financial applications, yet their suitability for this high-stakes domain remains largely unproven due to inadequacies in existing benchmarks. Existing benchmarks solely rely on score-level evaluation, summarizing performance with a single score that obscures the nuanced understanding of what models truly know and their precise limitations. They also rely on datasets that cover only a narrow subset of financial concepts, while overlooking other essentials for real-world applications. To address these gaps, we introduce FinCDM, the first cognitive diagnosis evaluation framework tailored for financial LLMs, enabling the evaluation of LLMs at the knowledge-skill level, identifying what financial skills and knowledge they have or lack based on their response patterns across skill-tagged tasks, rather than a single aggregated number. We construct CPA-QKA, the first cognitively informed financial evaluation dataset derived from the Certified Public Accountant (CPA) examination, with comprehensive coverage of real-world accounting and financial skills. It is rigorously annotated by domain experts, who author, validate, and annotate questions with high inter-annotator agreement and fine-grained knowledge labels. Our extensive experiments on 30 proprietary, open-source, and domain-specific LLMs show that FinCDM reveals hidden knowledge gaps, identifies under-tested areas such as tax and regulatory reasoning overlooked by traditional benchmarks, and uncovers behavioral clusters among models. FinCDM introduces a new paradigm for financial LLM evaluation by enabling interpretable, skill-aware diagnosis that supports more trustworthy and targeted model development, and all datasets and evaluation scripts will be publicly released to support further research.

Despite Greece's pivotal role in the global economy, large language models (LLMs) remain underexplored for Greek financial context due to the linguistic complexity of Greek and the scarcity of domain-specific datasets. Previous efforts in multilingual financial natural language processing (NLP) have exposed considerable performance disparities, yet no dedicated Greek financial benchmarks or Greek-specific financial LLMs have been developed until now. To bridge this gap, we introduce Plutus-ben, the first Greek Financial Evaluation Benchmark, and Plutus-8B, the pioneering Greek Financial LLM, fine-tuned with Greek domain-specific data. Plutus-ben addresses five core financial NLP tasks in Greek: numeric and textual named entity recognition, question answering, abstractive summarization, and topic classification, thereby facilitating systematic and reproducible LLM assessments. To underpin these tasks, we present three novel, high-quality Greek financial datasets, thoroughly annotated by expert native Greek speakers, augmented by two existing resources. Our comprehensive evaluation of 22 LLMs on Plutus-ben reveals that Greek financial NLP remains challenging due to linguistic complexity, domain-specific terminology, and financial reasoning gaps. These findings underscore the limitations of cross-lingual transfer, the necessity for financial expertise in Greek-trained models, and the challenges of adapting financial LLMs to Greek text. We release Plutus-ben, Plutus-8B, and all associated datasets publicly to promote reproducible research and advance Greek financial NLP, fostering broader multilingual inclusivity in finance.

In recent years, multimodal benchmarks for general domains have guided the rapid development of multimodal models on general tasks. However, the financial field has its peculiarities. It features unique graphical images (e.g., candlestick charts, technical indicator charts) and possesses a wealth of specialized financial knowledge (e.g., futures, turnover rate). Therefore, benchmarks from general fields often fail to measure the performance of multimodal models in the financial domain, and thus cannot effectively guide the rapid development of large financial models. To promote the development of large financial multimodal models, we propose MME-Finance, an bilingual open-ended and practical usage-oriented Visual Question Answering (VQA) benchmark. The characteristics of our benchmark are finance and expertise, which include constructing charts that reflect the actual usage needs of users (e.g., computer screenshots and mobile photography), creating questions according to the preferences in financial domain inquiries, and annotating questions by experts with 10+ years of experience in the financial industry. Additionally, we have developed a custom-designed financial evaluation system in which visual information is first introduced in the multi-modal evaluation process. Extensive experimental evaluations of 19 mainstream MLLMs are conducted to test their perception, reasoning, and cognition capabilities. The results indicate that models performing well on general benchmarks cannot do well on MME-Finance; for instance, the top-performing open-source and closed-source models obtain 65.69 (Qwen2VL-72B) and 63.18 (GPT-4o), respectively. Their performance is particularly poor in categories most relevant to finance, such as candlestick charts and technical indicator charts. In addition, we propose a Chinese version, which helps compare performance of MLLMs under a Chinese context.

Large language models (LLMs) have demonstrated exceptional performance in various natural language processing tasks, yet their efficacy in more challenging and domain-specific tasks remains largely unexplored. This paper presents FinEval, a benchmark specifically designed for the financial domain knowledge in the LLMs. FinEval is a collection of high-quality multiple-choice questions covering Finance, Economy, Accounting, and Certificate. It includes 4,661 questions spanning 34 different academic subjects. To ensure a comprehensive model performance evaluation, FinEval employs a range of prompt types, including zero-shot and few-shot prompts, as well as answer-only and chain-of-thought prompts. Evaluating state-of-the-art Chinese and English LLMs on FinEval, the results show that only GPT-4 achieved an accuracy close to 70% in different prompt settings, indicating significant growth potential for LLMs in the financial domain knowledge. Our work offers a more comprehensive financial knowledge evaluation benchmark, utilizing data of mock exams and covering a wide range of evaluated LLMs.

Recent advances in large language models (LLMs) have accelerated progress in financial NLP and applications, yet existing benchmarks remain limited to monolingual and unimodal settings, often over-relying on simple tasks and failing to reflect the complexity of real-world financial communication. We introduce MultiFinBen, the first multilingual and multimodal benchmark tailored to the global financial domain, evaluating LLMs across modalities (text, vision, audio) and linguistic settings (monolingual, bilingual, multilingual) on domain-specific tasks. We introduce two novel tasks, including PolyFiQA-Easy and PolyFiQA-Expert, the first multilingual financial benchmarks requiring models to perform complex reasoning over mixed-language inputs; and EnglishOCR and SpanishOCR, the first OCR-embedded financial QA tasks challenging models to extract and reason over information from visual-text financial documents. Moreover, we propose a dynamic, difficulty-aware selection mechanism and curate a compact, balanced benchmark rather than simple aggregation existing datasets. Extensive evaluation of 22 state-of-the-art models reveals that even the strongest models, despite their general multimodal and multilingual capabilities, struggle dramatically when faced with complex cross-lingual and multimodal tasks in financial domain. MultiFinBen is publicly released to foster transparent, reproducible, and inclusive progress in financial studies and applications.

Search has emerged as core infrastructure for LLM-based agents and is widely viewed as critical on the path toward more general intelligence. Finance is a particularly demanding proving ground: analysts routinely conduct complex, multi-step searches over time-sensitive, domain-specific data, making it ideal for assessing both search proficiency and knowledge-grounded reasoning. Yet no existing open financial datasets evaluate data searching capability of end-to-end agents, largely because constructing realistic, complicated tasks requires deep financial expertise and time-sensitive data is hard to evaluate. We present FinSearchComp, the first fully open-source agent benchmark for realistic, open-domain financial search and reasoning. FinSearchComp comprises three tasks -- Time-Sensitive Data Fetching, Simple Historical Lookup, and Complex Historical Investigation -- closely reproduce real-world financial analyst workflows. To ensure difficulty and reliability, we engage 70 professional financial experts for annotation and implement a rigorous multi-stage quality-assurance pipeline. The benchmark includes 635 questions spanning global and Greater China markets, and we evaluate 21 models (products) on it. Grok 4 (web) tops the global subset, approaching expert-level accuracy. DouBao (web) leads on the Greater China subset. Experimental analyses show that equipping agents with web search and financial plugins substantially improves results on FinSearchComp, and the country origin of models and tools impact performance significantly.By aligning with realistic analyst tasks and providing end-to-end evaluation, FinSearchComp offers a professional, high-difficulty testbed for complex financial search and reasoning.

In light of recent breakthroughs in large language models (LLMs) that have revolutionized natural language processing (NLP), there is an urgent need for new benchmarks to keep pace with the fast development of LLMs. In this paper, we propose CFLUE, the Chinese Financial Language Understanding Evaluation benchmark, designed to assess the capability of LLMs across various dimensions. Specifically, CFLUE provides datasets tailored for both knowledge assessment and application assessment. In knowledge assessment, it consists of 38K+ multiple-choice questions with associated solution explanations. These questions serve dual purposes: answer prediction and question reasoning. In application assessment, CFLUE features 16K+ test instances across distinct groups of NLP tasks such as text classification, machine translation, relation extraction, reading comprehension, and text generation. Upon CFLUE, we conduct a thorough evaluation of representative LLMs. The results reveal that only GPT-4 and GPT-4-turbo achieve an accuracy exceeding 60\% in answer prediction for knowledge assessment, suggesting that there is still substantial room for improvement in current LLMs. In application assessment, although GPT-4 and GPT-4-turbo are the top two performers, their considerable advantage over lightweight LLMs is noticeably diminished. The datasets and scripts associated with CFLUE are openly accessible at https://github.com/aliyun/cflue.

Recent breakthroughs in large language models (LLMs) have led to the development of new benchmarks for evaluating their performance in the financial domain. However, current financial benchmarks often rely on news articles, earnings reports, or announcements, making it challenging to capture the real-world dynamics of financial meetings. To address this gap, we propose a novel benchmark called M^3FinMeeting, which is a multilingual, multi-sector, and multi-task dataset designed for financial meeting understanding. First, M^3FinMeeting supports English, Chinese, and Japanese, enhancing comprehension of financial discussions in diverse linguistic contexts. Second, it encompasses various industry sectors defined by the Global Industry Classification Standard (GICS), ensuring that the benchmark spans a broad range of financial activities. Finally, M^3FinMeeting includes three tasks: summarization, question-answer (QA) pair extraction, and question answering, facilitating a more realistic and comprehensive evaluation of understanding. Experimental results with seven popular LLMs reveal that even the most advanced long-context models have significant room for improvement, demonstrating the effectiveness of M^3FinMeeting as a benchmark for assessing LLMs' financial meeting comprehension skills.

Although large language models (LLMs) has shown great performance on natural language processing (NLP) in the financial domain, there are no publicly available financial tailtored LLMs, instruction tuning datasets, and evaluation benchmarks, which is critical for continually pushing forward the open-source development of financial artificial intelligence (AI). This paper introduces PIXIU, a comprehensive framework including the first financial LLM based on fine-tuning LLaMA with instruction data, the first instruction data with 136K data samples to support the fine-tuning, and an evaluation benchmark with 5 tasks and 9 datasets. We first construct the large-scale multi-task instruction data considering a variety of financial tasks, financial document types, and financial data modalities. We then propose a financial LLM called FinMA by fine-tuning LLaMA with the constructed dataset to be able to follow instructions for various financial tasks. To support the evaluation of financial LLMs, we propose a standardized benchmark that covers a set of critical financial tasks, including five financial NLP tasks and one financial prediction task. With this benchmark, we conduct a detailed analysis of FinMA and several existing LLMs, uncovering their strengths and weaknesses in handling critical financial tasks. The model, datasets, benchmark, and experimental results are open-sourced to facilitate future research in financial AI.

Pre-trained language models have shown impressive performance on a variety of tasks and domains. Previous research on financial language models usually employs a generic training scheme to train standard model architectures, without completely leveraging the richness of the financial data. We propose a novel domain specific Financial LANGuage model (FLANG) which uses financial keywords and phrases for better masking, together with span boundary objective and in-filing objective. Additionally, the evaluation benchmarks in the field have been limited. To this end, we contribute the Financial Language Understanding Evaluation (FLUE), an open-source comprehensive suite of benchmarks for the financial domain. These include new benchmarks across 5 NLP tasks in financial domain as well as common benchmarks used in the previous research. Experiments on these benchmarks suggest that our model outperforms those in prior literature on a variety of NLP tasks. Our models, code and benchmark data are publicly available on Github and Huggingface.

Although Large Language Model (LLM)-based agents are increasingly used in financial trading, it remains unclear whether they can reason and adapt in live markets, as most studies test models instead of agents, cover limited periods and assets, and rely on unverified data. To address these gaps, we introduce Agent Market Arena (AMA), the first lifelong, real-time benchmark for evaluating LLM-based trading agents across multiple markets. AMA integrates verified trading data, expert-checked news, and diverse agent architectures within a unified trading framework, enabling fair and continuous comparison under real conditions. It implements four agents, including InvestorAgent as a single-agent baseline, TradeAgent and HedgeFundAgent with different risk styles, and DeepFundAgent with memory-based reasoning, and evaluates them across GPT-4o, GPT-4.1, Claude-3.5-haiku, Claude-sonnet-4, and Gemini-2.0-flash. Live experiments on both cryptocurrency and stock markets demonstrate that agent frameworks display markedly distinct behavioral patterns, spanning from aggressive risk-taking to conservative decision-making, whereas model backbones contribute less to outcome variation. AMA thus establishes a foundation for rigorous, reproducible, and continuously evolving evaluation of financial reasoning and trading intelligence in LLM-based agents.

Long-context large language models (LC LLMs) promise to increase reliability of LLMs in real-world tasks requiring processing and understanding of long input documents. However, this ability of LC LLMs to reliably utilize their growing context windows remains under investigation. In this work, we evaluate the performance of state-of-the-art GPT-4 suite of LC LLMs in solving a series of progressively challenging tasks, as a function of factors such as context length, task difficulty, and position of key information by creating a real world financial news dataset. Our findings indicate that LC LLMs exhibit brittleness at longer context lengths even for simple tasks, with performance deteriorating sharply as task complexity increases. At longer context lengths, these state-of-the-art models experience catastrophic failures in instruction following resulting in degenerate outputs. Our prompt ablations also reveal unfortunate continued sensitivity to both the placement of the task instruction in the context window as well as minor markdown formatting. Finally, we advocate for more rigorous evaluation of LC LLMs by employing holistic metrics such as F1 (rather than recall) and reporting confidence intervals, thereby ensuring robust and conclusive findings.

We introduce FinCriticalED (Financial Critical Error Detection), a visual benchmark for evaluating OCR and vision language models on financial documents at the fact level. Financial documents contain visually dense and table heavy layouts where numerical and temporal information is tightly coupled with structure. In high stakes settings, small OCR mistakes such as sign inversion or shifted dates can lead to materially different interpretations, while traditional OCR metrics like ROUGE and edit distance capture only surface level text similarity. \ficriticaled provides 500 image-HTML pairs with expert annotated financial facts covering over seven hundred numerical and temporal facts. It introduces three key contributions. First, it establishes the first fact level evaluation benchmark for financial document understanding, shifting evaluation from lexical overlap to domain critical factual correctness. Second, all annotations are created and verified by financial experts with strict quality control over signs, magnitudes, and temporal expressions. Third, we develop an LLM-as-Judge evaluation pipeline that performs structured fact extraction and contextual verification for visually complex financial documents. We benchmark OCR systems, open source vision language models, and proprietary models on FinCriticalED. Results show that although the strongest proprietary models achieve the highest factual accuracy, substantial errors remain in visually intricate numerical and temporal contexts. Through quantitative evaluation and expert case studies, FinCriticalED provides a rigorous foundation for advancing visual factual precision in financial and other precision critical domains.

Multimodal Large Language Models (MLLMs) have experienced rapid development in recent years. However, in the financial domain, there is a notable lack of effective and specialized multimodal evaluation datasets. To advance the development of MLLMs in the finance domain, we introduce FinMME, encompassing more than 11,000 high-quality financial research samples across 18 financial domains and 6 asset classes, featuring 10 major chart types and 21 subtypes. We ensure data quality through 20 annotators and carefully designed validation mechanisms. Additionally, we develop FinScore, an evaluation system incorporating hallucination penalties and multi-dimensional capability assessment to provide an unbiased evaluation. Extensive experimental results demonstrate that even state-of-the-art models like GPT-4o exhibit unsatisfactory performance on FinMME, highlighting its challenging nature. The benchmark exhibits high robustness with prediction variations under different prompts remaining below 1%, demonstrating superior reliability compared to existing datasets. Our dataset and evaluation protocol are available at https://huggingface.co/datasets/luojunyu/FinMME and https://github.com/luo-junyu/FinMME.

This paper explores the potential of large language models (LLMs) to generate financial reports from time series data. We propose a framework encompassing prompt engineering, model selection, and evaluation. We introduce an automated highlighting system to categorize information within the generated reports, differentiating between insights derived directly from time series data, stemming from financial reasoning, and those reliant on external knowledge. This approach aids in evaluating the factual grounding and reasoning capabilities of the models. Our experiments, utilizing both data from the real stock market indices and synthetic time series, demonstrate the capability of LLMs to produce coherent and informative financial reports.

Generative chat models, such as ChatGPT and GPT-4, have revolutionized natural language generation (NLG) by incorporating instructions and human feedback to achieve significant performance improvements. However, the lack of standardized evaluation benchmarks for chat models, particularly for Chinese and domain-specific models, hinders their assessment and progress. To address this gap, we introduce the Chinese Generative Chat Evaluation (CGCE) benchmark, focusing on general and financial domains. The CGCE benchmark encompasses diverse tasks, including 200 questions in the general domain and 150 specific professional questions in the financial domain. Manual scoring evaluates factors such as accuracy, coherence, expression clarity, and completeness. The CGCE benchmark provides researchers with a standardized framework to assess and compare Chinese generative chat models, fostering advancements in NLG research.

Large Language Models (LLMs) have demonstrated remarkable performance on a wide range of Natural Language Processing (NLP) tasks, often matching or even beating state-of-the-art task-specific models. This study aims at assessing the financial reasoning capabilities of LLMs. We leverage mock exam questions of the Chartered Financial Analyst (CFA) Program to conduct a comprehensive evaluation of ChatGPT and GPT-4 in financial analysis, considering Zero-Shot (ZS), Chain-of-Thought (CoT), and Few-Shot (FS) scenarios. We present an in-depth analysis of the models' performance and limitations, and estimate whether they would have a chance at passing the CFA exams. Finally, we outline insights into potential strategies and improvements to enhance the applicability of LLMs in finance. In this perspective, we hope this work paves the way for future studies to continue enhancing LLMs for financial reasoning through rigorous evaluation.

FinanceQA is a testing suite that evaluates LLMs' performance on complex numerical financial analysis tasks that mirror real-world investment work. Despite recent advances, current LLMs fail to meet the strict accuracy requirements of financial institutions, with models failing approximately 60% of realistic tasks that mimic on-the-job analyses at hedge funds, private equity firms, investment banks, and other financial institutions. The primary challenges include hand-spreading metrics, adhering to standard accounting and corporate valuation conventions, and performing analysis under incomplete information - particularly in multi-step tasks requiring assumption generation. This performance gap highlights the disconnect between existing LLM capabilities and the demands of professional financial analysis that are inadequately tested by current testing architectures. Results show that higher-quality training data is needed to support such tasks, which we experiment with using OpenAI's fine-tuning API. FinanceQA is publicly released at [this https URL](https://huggingface.co/datasets/AfterQuery/FinanceQA).

Large language models (LLMs) have recently demonstrated strong capabilities as autonomous agents, showing promise in reasoning, tool use, and sequential decision-making. While prior benchmarks have evaluated LLM agents in domains such as software engineering and scientific discovery, the finance domain remains underexplored, despite its direct relevance to economic value and high-stakes decision-making. Existing financial benchmarks primarily test static knowledge through question answering, but they fall short of capturing the dynamic and iterative nature of trading. To address this gap, we introduce StockBench, a contamination-free benchmark designed to evaluate LLM agents in realistic, multi-month stock trading environments. Agents receive daily market signals -- including prices, fundamentals, and news -- and must make sequential buy, sell, or hold decisions. Performance is assessed using financial metrics such as cumulative return, maximum drawdown, and the Sortino ratio. Our evaluation of state-of-the-art proprietary (e.g., GPT-5, Claude-4) and open-weight (e.g., Qwen3, Kimi-K2, GLM-4.5) models shows that while most LLM agents struggle to outperform the simple buy-and-hold baseline, several models demonstrate the potential to deliver higher returns and manage risk more effectively. These findings highlight both the challenges and opportunities in developing LLM-powered financial agents, showing that excelling at static financial knowledge tasks does not necessarily translate into successful trading strategies. We release StockBench as an open-source resource to support reproducibility and advance future research in this domain.

Financial report generation tasks range from macro- to micro-economics analysis, also requiring extensive data analysis. Existing LLM models are usually fine-tuned on simple QA tasks and cannot comprehensively analyze real financial scenarios. Given the complexity, financial companies often distribute tasks among departments. Inspired by this, we propose FinTeam, a financial multi-agent collaborative system, with a workflow with four LLM agents: document analyzer, analyst, accountant, and consultant. We train these agents with specific financial expertise using constructed datasets. We evaluate FinTeam on comprehensive financial tasks constructed from real online investment forums, including macroeconomic, industry, and company analysis. The human evaluation shows that by combining agents, the financial reports generate from FinTeam achieved a 62.00% acceptance rate, outperforming baseline models like GPT-4o and Xuanyuan. Additionally, FinTeam's agents demonstrate a 7.43% average improvement on FinCUGE and a 2.06% accuracy boost on FinEval. Project is available at https://github.com/FudanDISC/DISC-FinLLM/.

Large vision-language models (LVLMs) have made significant progress in chart understanding. However, financial charts, characterized by complex temporal structures and domain-specific terminology, remain notably underexplored. We introduce FinChart-Bench, the first benchmark specifically focused on real-world financial charts. FinChart-Bench comprises 1,200 financial chart images collected from 2015 to 2024, each annotated with True/False (TF), Multiple Choice (MC), and Question Answering (QA) questions, totaling 7,016 questions. We conduct a comprehensive evaluation of 25 state-of-the-art LVLMs on FinChart-Bench. Our evaluation reveals critical insights: (1) the performance gap between open-source and closed-source models is narrowing, (2) performance degradation occurs in upgraded models within families, (3) many models struggle with instruction following, (4) both advanced models show significant limitations in spatial reasoning abilities, and (5) current LVLMs are not reliable enough to serve as automated evaluators. These findings highlight important limitations in current LVLM capabilities for financial chart understanding. The FinChart-Bench dataset is available at https://huggingface.co/datasets/Tizzzzy/FinChart-Bench.

We propose two new methods for multi-document financial question answering. First, a method that uses semantic tagging, and then, queries the index to get the context (RAG_SEM). And second, a Knowledge Graph (KG_RAG) based method that uses semantic tagging, and, retrieves knowledge graph triples from a graph database, as context. KG_RAG uses knowledge graphs constructed using a small model that is fine-tuned using knowledge distillation using a large teacher model. The data consists of 18 10K reports of Apple, Microsoft, Alphabet, NVIDIA, Amazon and Tesla for the years 2021, 2022 and 2023. The list of questions in the data consists of 111 complex questions including many esoteric questions that are difficult to answer and the answers are not completely obvious. As evaluation metrics, we use overall scores as well as segmented scores for measurement including the faithfulness, relevance, correctness, similarity, an LLM based overall score and the rouge scores as well as a similarity of embeddings. We find that both methods outperform plain RAG significantly. KG_RAG outperforms RAG_SEM in four out of nine metrics.

Large language models excel in general tasks, yet assessing their reliability in logic-heavy, precision-critical domains like finance, law, and healthcare remains challenging. To address this, we introduce BizFinBench, the first benchmark specifically designed to evaluate LLMs in real-world financial applications. BizFinBench consists of 6,781 well-annotated queries in Chinese, spanning five dimensions: numerical calculation, reasoning, information extraction, prediction recognition, and knowledge-based question answering, grouped into nine fine-grained categories. The benchmark includes both objective and subjective metrics. We also introduce IteraJudge, a novel LLM evaluation method that reduces bias when LLMs serve as evaluators in objective metrics. We benchmark 25 models, including both proprietary and open-source systems. Extensive experiments show that no model dominates across all tasks. Our evaluation reveals distinct capability patterns: (1) In Numerical Calculation, Claude-3.5-Sonnet (63.18) and DeepSeek-R1 (64.04) lead, while smaller models like Qwen2.5-VL-3B (15.92) lag significantly; (2) In Reasoning, proprietary models dominate (ChatGPT-o3: 83.58, Gemini-2.0-Flash: 81.15), with open-source models trailing by up to 19.49 points; (3) In Information Extraction, the performance spread is the largest, with DeepSeek-R1 scoring 71.46, while Qwen3-1.7B scores 11.23; (4) In Prediction Recognition, performance variance is minimal, with top models scoring between 39.16 and 50.00. We find that while current LLMs handle routine finance queries competently, they struggle with complex scenarios requiring cross-concept reasoning. BizFinBench offers a rigorous, business-aligned benchmark for future research. The code and dataset are available at https://github.com/HiThink-Research/BizFinBench.

In the fast-paced financial domain, accurate and up-to-date information is critical to addressing ever-evolving market conditions. Retrieving this information correctly is essential in financial Question-Answering (QA), since many language models struggle with factual accuracy in this domain. We present FinDER, an expert-generated dataset tailored for Retrieval-Augmented Generation (RAG) in finance. Unlike existing QA datasets that provide predefined contexts and rely on relatively clear and straightforward queries, FinDER focuses on annotating search-relevant evidence by domain experts, offering 5,703 query-evidence-answer triplets derived from real-world financial inquiries. These queries frequently include abbreviations, acronyms, and concise expressions, capturing the brevity and ambiguity common in the realistic search behavior of professionals. By challenging models to retrieve relevant information from large corpora rather than relying on readily determined contexts, FinDER offers a more realistic benchmark for evaluating RAG systems. We further present a comprehensive evaluation of multiple state-of-the-art retrieval models and Large Language Models, showcasing challenges derived from a realistic benchmark to drive future research on truthful and precise RAG in the financial domain.

This comprehensive study evaluates the performance of OpenAI's o1-preview large language model across a diverse array of complex reasoning tasks, spanning multiple domains, including computer science, mathematics, natural sciences, medicine, linguistics, and social sciences. Through rigorous testing, o1-preview demonstrated remarkable capabilities, often achieving human-level or superior performance in areas ranging from coding challenges to scientific reasoning and from language processing to creative problem-solving. Key findings include: -83.3% success rate in solving complex competitive programming problems, surpassing many human experts. -Superior ability in generating coherent and accurate radiology reports, outperforming other evaluated models. -100% accuracy in high school-level mathematical reasoning tasks, providing detailed step-by-step solutions. -Advanced natural language inference capabilities across general and specialized domains like medicine. -Impressive performance in chip design tasks, outperforming specialized models in areas such as EDA script generation and bug analysis. -Remarkable proficiency in anthropology and geology, demonstrating deep understanding and reasoning in these specialized fields. -Strong capabilities in quantitative investing. O1 has comprehensive financial knowledge and statistical modeling skills. -Effective performance in social media analysis, including sentiment analysis and emotion recognition. The model excelled particularly in tasks requiring intricate reasoning and knowledge integration across various fields. While some limitations were observed, including occasional errors on simpler problems and challenges with certain highly specialized concepts, the overall results indicate significant progress towards artificial general intelligence.

Financial news plays a crucial role in decision-making processes across the financial sector, yet the efficient processing of this information into a structured format remains challenging. This paper presents a novel approach to financial news processing that leverages Large Language Models (LLMs) to overcome limitations that previously prevented the extraction of structured data from unstructured financial news. We introduce a system that extracts relevant company tickers from raw news article content, performs sentiment analysis at the company level, and generates summaries, all without relying on pre-structured data feeds. Our methodology combines the generative capabilities of LLMs, and recent prompting techniques, with a robust validation framework that uses a tailored string similarity approach. Evaluation on a dataset of 5530 financial news articles demonstrates the effectiveness of our approach, with 90% of articles not missing any tickers compared with current data providers, and 22% of articles having additional relevant tickers. In addition to this paper, the methodology has been implemented at scale with the resulting processed data made available through a live API endpoint, which is updated in real-time with the latest news. To the best of our knowledge, we are the first data provider to offer granular, per-company sentiment analysis from news articles, enhancing the depth of information available to market participants. We also release the evaluation dataset of 5530 processed articles as a static file, which we hope will facilitate further research leveraging financial news.

Retrieval-Augmented Generation (RAG) systems face significant performance gaps when applied to technical domains requiring precise information extraction from complex documents. Current evaluation methodologies relying on document-level metrics inadequately capture token-resolution retrieval accuracy that is critical for domain-related documents. We propose a framework combining granular evaluation metrics with synthetic data generation to optimize domain-specific RAG performance. First, we introduce token-aware metrics Precision Omega and Intersection-over-Union (IoU) that quantify context preservation versus information density trade-offs inherent in technical texts. Second, we develop a reasoning model-driven pipeline using instruction-tuned LLMs (DeepSeek-R1, DeepSeek-R1 distilled variants, and Phi-4) to generate context-anchored QA pairs with discontinuous reference spans across three specialized corpora: SEC 10-K filings (finance), biomedical abstracts (PubMed), and APT threat reports (cybersecurity). Our empirical analysis reveals critical insights: smaller chunks (less than 10 tokens) improve precision by 31-42% (IoU = 0.071 vs. baseline 0.053) at recall costs (-18%), while domain-specific embedding strategies yield 22% variance in optimal chunk sizing (5-20 tokens). The DeepSeek-R1-Distill-Qwen-32B model demonstrates superior concept alignment (+14% mean IoU over alternatives), though no configuration universally dominates. Financial texts favor larger chunks for risk factor coverage (Recall = 0.81 at size = 20), whereas cybersecurity content benefits from atomic segmentation, Precision Omega = 0.28 at size = 5. Our code is available on https://github.com/aryan-jadon/Synthetic-Data-Generation-and-Evaluation-using-Reasoning-Model

The complexity of the Generally Accepted Accounting Principles (GAAP) and the hierarchical structure of eXtensible Business Reporting Language (XBRL) filings make financial auditing increasingly difficult to automate and verify. While large language models (LLMs) have demonstrated strong capabilities in unstructured text understanding, their ability to reason over structured, interdependent, and taxonomy-driven financial documents remains largely unexplored. To fill this gap, we introduce FinAuditing, the first taxonomy-aligned, structure-aware, multi-document benchmark for evaluating LLMs on financial auditing tasks. Built from real US-GAAP-compliant XBRL filings, FinAuditing defines three complementary subtasks, FinSM for semantic consistency, FinRE for relational consistency, and FinMR for numerical consistency, each targeting a distinct aspect of structured auditing reasoning. We further propose a unified evaluation framework integrating retrieval, classification, and reasoning metrics across these subtasks. Extensive zero-shot experiments on 13 state-of-the-art LLMs reveal that current models perform inconsistently across semantic, relational, and mathematical dimensions, with accuracy drops of up to 60-90% when reasoning over hierarchical multi-document structures. Our findings expose the systematic limitations of modern LLMs in taxonomy-grounded financial reasoning and establish FinAuditing as a foundation for developing trustworthy, structure-aware, and regulation-aligned financial intelligence systems. The benchmark dataset is available at Hugging Face.

Audio Large Language Models (AudioLLMs) have received widespread attention and have significantly improved performance on audio tasks such as conversation, audio understanding, and automatic speech recognition (ASR). Despite these advancements, there is an absence of a benchmark for assessing AudioLLMs in financial scenarios, where audio data, such as earnings conference calls and CEO speeches, are crucial resources for financial analysis and investment decisions. In this paper, we introduce FinAudio, the first benchmark designed to evaluate the capacity of AudioLLMs in the financial domain. We first define three tasks based on the unique characteristics of the financial domain: 1) ASR for short financial audio, 2) ASR for long financial audio, and 3) summarization of long financial audio. Then, we curate two short and two long audio datasets, respectively, and develop a novel dataset for financial audio summarization, comprising the FinAudio benchmark. Then, we evaluate seven prevalent AudioLLMs on FinAudio. Our evaluation reveals the limitations of existing AudioLLMs in the financial domain and offers insights for improving AudioLLMs. All datasets and codes will be released.

Large Language Models (LLMs) exhibit considerable promise in financial applications; however, prevailing models frequently demonstrate limitations when confronted with scenarios that necessitate sophisticated reasoning capabilities, stringent trustworthiness criteria, and efficient adaptation to domain-specific requirements. We introduce the Agentar-Fin-R1 series of financial large language models (8B and 32B parameters), specifically engineered based on the Qwen3 foundation model to enhance reasoning capabilities, reliability, and domain specialization for financial applications. Our optimization approach integrates a high-quality, systematic financial task label system with a comprehensive multi-layered trustworthiness assurance framework. This framework encompasses high-quality trustworthy knowledge engineering, multi-agent trustworthy data synthesis, and rigorous data validation governance. Through label-guided automated difficulty-aware optimization, tow-stage training pipeline, and dynamic attribution systems, we achieve substantial improvements in training efficiency. Our models undergo comprehensive evaluation on mainstream financial benchmarks including Fineva, FinEval, and FinanceIQ, as well as general reasoning datasets such as MATH-500 and GPQA-diamond. To thoroughly assess real-world deployment capabilities, we innovatively propose the Finova evaluation benchmark, which focuses on agent-level financial reasoning and compliance verification. Experimental results demonstrate that Agentar-Fin-R1 not only achieves state-of-the-art performance on financial tasks but also exhibits exceptional general reasoning capabilities, validating its effectiveness as a trustworthy solution for high-stakes financial applications. The Finova bench is available at https://github.com/antgroup/Finova.

Deep Research (DR) agents, powered by advanced Large Language Models (LLMs), have recently garnered increasing attention for their capability in conducting complex research tasks. However, existing literature lacks a rigorous and systematic evaluation of DR Agent's capabilities in critical research analysis. To address this gap, we first propose HisRubric, a novel evaluation framework with a hierarchical analytical structure and a fine-grained grading rubric for rigorously assessing DR agents' capabilities in corporate financial analysis. This framework mirrors the professional analyst's workflow, progressing from data recognition to metric calculation, and finally to strategic summarization and interpretation. Built on this framework, we construct a FinDeepResearch benchmark that comprises 64 listed companies from 8 financial markets across 4 languages, encompassing a total of 15,808 grading items. We further conduct extensive experiments on the FinDeepResearch using 16 representative methods, including 6 DR agents, 5 LLMs equipped with both deep reasoning and search capabilities, and 5 LLMs with deep reasoning capabilities only. The results reveal the strengths and limitations of these approaches across diverse capabilities, financial markets, and languages, offering valuable insights for future research and development. The benchmark and evaluation code will be made publicly available.

We present a new financial domain large language model, InvestLM, tuned on LLaMA-65B (Touvron et al., 2023), using a carefully curated instruction dataset related to financial investment. Inspired by less-is-more-for-alignment (Zhou et al., 2023), we manually curate a small yet diverse instruction dataset, covering a wide range of financial related topics, from Chartered Financial Analyst (CFA) exam questions to SEC filings to Stackexchange quantitative finance discussions. InvestLM shows strong capabilities in understanding financial text and provides helpful responses to investment related questions. Financial experts, including hedge fund managers and research analysts, rate InvestLM's response as comparable to those of state-of-the-art commercial models (GPT-3.5, GPT-4 and Claude-2). Zero-shot evaluation on a set of financial NLP benchmarks demonstrates strong generalizability. From a research perspective, this work suggests that a high-quality domain specific LLM can be tuned using a small set of carefully curated instructions on a well-trained foundation model, which is consistent with the Superficial Alignment Hypothesis (Zhou et al., 2023). From a practical perspective, this work develops a state-of-the-art financial domain LLM with superior capability in understanding financial texts and providing helpful investment advice, potentially enhancing the work efficiency of financial professionals. We release the model parameters to the research community.

Accurate information retrieval (IR) is critical in the financial domain, where investors must identify relevant information from large collections of documents. Traditional IR methods -- whether sparse or dense -- often fall short in retrieval accuracy, as it requires not only capturing semantic similarity but also performing fine-grained reasoning over document structure and domain-specific knowledge. Recent advances in large language models (LLMs) have opened up new opportunities for retrieval with multi-step reasoning, where the model ranks passages through iterative reasoning about which information is most relevant to a given query. However, there exists no benchmark to evaluate such capabilities in the financial domain. To address this gap, we introduce FinAgentBench, the first large-scale benchmark for evaluating retrieval with multi-step reasoning in finance -- a setting we term agentic retrieval. The benchmark consists of 26K expert-annotated examples on S&P-500 listed firms and assesses whether LLM agents can (1) identify the most relevant document type among candidates, and (2) pinpoint the key passage within the selected document. Our evaluation framework explicitly separates these two reasoning steps to address context limitations. This design enables to provide a quantitative basis for understanding retrieval-centric LLM behavior in finance. We evaluate a suite of state-of-the-art models and further demonstrated how targeted fine-tuning can significantly improve agentic retrieval performance. Our benchmark provides a foundation for studying retrieval-centric LLM behavior in complex, domain-specific tasks for finance.

Large language models (LLMs) have achieved remarkable performance on various NLP tasks, yet their potential in more challenging and domain-specific task, such as finance, has not been fully explored. In this paper, we present CFinBench: a meticulously crafted, the most comprehensive evaluation benchmark to date, for assessing the financial knowledge of LLMs under Chinese context. In practice, to better align with the career trajectory of Chinese financial practitioners, we build a systematic evaluation from 4 first-level categories: (1) Financial Subject: whether LLMs can memorize the necessary basic knowledge of financial subjects, such as economics, statistics and auditing. (2) Financial Qualification: whether LLMs can obtain the needed financial qualified certifications, such as certified public accountant, securities qualification and banking qualification. (3) Financial Practice: whether LLMs can fulfill the practical financial jobs, such as tax consultant, junior accountant and securities analyst. (4) Financial Law: whether LLMs can meet the requirement of financial laws and regulations, such as tax law, insurance law and economic law. CFinBench comprises 99,100 questions spanning 43 second-level categories with 3 question types: single-choice, multiple-choice and judgment. We conduct extensive experiments of 50 representative LLMs with various model size on CFinBench. The results show that GPT4 and some Chinese-oriented models lead the benchmark, with the highest average accuracy being 60.16%, highlighting the challenge presented by CFinBench. The dataset and evaluation code are available at https://cfinbench.github.io/.

A number of datasets for Relation Extraction (RE) have been created to aide downstream tasks such as information retrieval, semantic search, question answering and textual entailment. However, these datasets fail to capture financial-domain specific challenges since most of these datasets are compiled using general knowledge sources such as Wikipedia, web-based text and news articles, hindering real-life progress and adoption within the financial world. To address this limitation, we propose REFinD, the first large-scale annotated dataset of relations, with sim29K instances and 22 relations amongst 8 types of entity pairs, generated entirely over financial documents. We also provide an empirical evaluation with various state-of-the-art models as benchmarks for the RE task and highlight the challenges posed by our dataset. We observed that various state-of-the-art deep learning models struggle with numeric inference, relational and directional ambiguity.

Artificial intelligence is making significant strides in the finance industry, revolutionizing how data is processed and interpreted. Among these technologies, large language models (LLMs) have demonstrated substantial potential to transform financial services by automating complex tasks, enhancing customer service, and providing detailed financial analysis. Firstly, we introduce IDEA-FinBench, an evaluation benchmark specifically tailored for assessing financial knowledge in large language models (LLMs). This benchmark utilizes questions from two globally respected and authoritative financial professional exams, aimimg to comprehensively evaluate the capability of LLMs to directly address exam questions pertinent to the finance sector. Secondly, we propose IDEA-FinKER, a Financial Knowledge Enhancement framework designed to facilitate the rapid adaptation of general LLMs to the financial domain, introducing a retrieval-based few-shot learning method for real-time context-level knowledge injection, and a set of high-quality financial knowledge instructions for fine-tuning any general LLM. Finally, we present IDEA-FinQA, a financial question-answering system powered by LLMs. This system is structured around a scheme of real-time knowledge injection and factual enhancement using external knowledge. IDEA-FinQA is comprised of three main modules: the data collector, the data querying module, and LLM-based agents tasked with specific functions.

While the progression of Large Language Models (LLMs) has notably propelled financial analysis, their application has largely been confined to singular language realms, leaving untapped the potential of bilingual Chinese-English capacity. To bridge this chasm, we introduce ICE-PIXIU, seamlessly amalgamating the ICE-INTENT model and ICE-FLARE benchmark for bilingual financial analysis. ICE-PIXIU uniquely integrates a spectrum of Chinese tasks, alongside translated and original English datasets, enriching the breadth and depth of bilingual financial modeling. It provides unrestricted access to diverse model variants, a substantial compilation of diverse cross-lingual and multi-modal instruction data, and an evaluation benchmark with expert annotations, comprising 10 NLP tasks, 20 bilingual specific tasks, totaling 1,185k datasets. Our thorough evaluation emphasizes the advantages of incorporating these bilingual datasets, especially in translation tasks and utilizing original English data, enhancing both linguistic flexibility and analytical acuity in financial contexts. Notably, ICE-INTENT distinguishes itself by showcasing significant enhancements over conventional LLMs and existing financial LLMs in bilingual milieus, underscoring the profound impact of robust bilingual data on the accuracy and efficacy of financial NLP.

Extracting tables and key-value pairs from financial documents is essential for business workflows such as auditing, data analytics, and automated invoice processing. In this work, we introduce Spatial ModernBERT-a transformer-based model augmented with spatial embeddings-to accurately detect and extract tabular data and key-value fields from complex financial documents. We cast the extraction task as token classification across three heads: (1) Label Head, classifying each token as a label (e.g., PO Number, PO Date, Item Description, Quantity, Base Cost, MRP, etc.); (2) Column Head, predicting column indices; (3) Row Head, distinguishing the start of item rows and header rows. The model is pretrained on the PubTables-1M dataset, then fine-tuned on a financial document dataset, achieving robust performance through cross-entropy loss on each classification head. We propose a post-processing method to merge tokens using B-I-IB tagging, reconstruct the tabular layout, and extract key-value pairs. Empirical evaluation shows that Spatial ModernBERT effectively leverages both textual and spatial cues, facilitating highly accurate table and key-value extraction in real-world financial documents.

Large language models (LLMs) have become powerful tools for advancing natural language processing applications in the financial industry. However, existing financial LLMs often face challenges such as hallucinations or superficial parameter training, resulting in suboptimal performance, particularly in financial computing and machine reading comprehension (MRC). To address these issues, we propose a novel large language model specifically designed for the Chinese financial domain, named SNFinLLM. SNFinLLM excels in domain-specific tasks such as answering questions, summarizing financial research reports, analyzing sentiment, and executing financial calculations. We then perform the supervised fine-tuning (SFT) to enhance the model's proficiency across various financial domains. Specifically, we gather extensive financial data and create a high-quality instruction dataset composed of news articles, professional papers, and research reports of finance domain. Utilizing both domain-specific and general datasets, we proceed with continuous pre-training on an established open-source base model, resulting in SNFinLLM-base. Following this, we engage in supervised fine-tuning (SFT) to bolster the model's capability across multiple financial tasks. Crucially, we employ a straightforward Direct Preference Optimization (DPO) method to better align the model with human preferences. Extensive experiments conducted on finance benchmarks and our evaluation dataset demonstrate that SNFinLLM markedly outperforms other state-of-the-art financial language models. For more details, check out our demo video here: https://www.youtube.com/watch?v=GYT-65HZwus.

Multi-step symbolic reasoning is critical for advancing downstream performance on financial tasks. Yet, benchmarks for systematically evaluating this capability are lacking. Existing datasets like FinQA and ConvFinQA supervise only final numerical answers, without assessing intermediate reasoning steps. To address this, we introduce FinChain, the first symbolic benchmark designed for verifiable Chain-of- Thought (CoT) financial reasoning. Spanning 54 topics across 12 financial domains, Fin- Chain offers five parameterized templates per topic, each varying in reasoning complexity and domain expertise required. Each dataset instance includes an executable Python trace, enabling automatic generation of extensive training data and easy adaptation to other domains. We also introduce ChainEval, a new metric for automatic evaluation of both final answers and intermediate reasoning. Benchmarking 30 LLMs on our dataset, we find that even state-of-the-art models have considerable room for improvement in multi-step financial reasoning. All templates and evaluation metrics for FinChain are available at https: //github.com/mbzuai-nlp/finchain.

Large Language Models (LLMs) have demonstrated remarkable potential as autonomous agents, approaching human-expert performance through advanced reasoning and tool orchestration. However, decision-making in fully dynamic and live environments remains highly challenging, requiring real-time information integration and adaptive responses. While existing efforts have explored live evaluation mechanisms in structured tasks, a critical gap remains in systematic benchmarking for real-world applications, particularly in finance where stringent requirements exist for live strategic responsiveness. To address this gap, we introduce AI-Trader, the first fully-automated, live, and data-uncontaminated evaluation benchmark for LLM agents in financial decision-making. AI-Trader spans three major financial markets: U.S. stocks, A-shares, and cryptocurrencies, with multiple trading granularities to simulate live financial environments. Our benchmark implements a revolutionary fully autonomous minimal information paradigm where agents receive only essential context and must independently search, verify, and synthesize live market information without human intervention. We evaluate six mainstream LLMs across three markets and multiple trading frequencies. Our analysis reveals striking findings: general intelligence does not automatically translate to effective trading capability, with most agents exhibiting poor returns and weak risk management. We demonstrate that risk control capability determines cross-market robustness, and that AI trading strategies achieve excess returns more readily in highly liquid markets than policy-driven environments. These findings expose critical limitations in current autonomous agents and provide clear directions for future improvements. The code and evaluation data are open-sourced to foster community research: https://github.com/HKUDS/AI-Trader.

Large Language Models (LLMs) frequently hallucinate to long-form questions, producing plausible yet factually incorrect answers. A common mitigation strategy is to provide attribution to LLM outputs. However, existing benchmarks primarily focus on simple attribution that retrieves supporting textual evidence as references. We argue that in real-world scenarios such as financial applications, attribution goes beyond reference retrieval. We introduce FinLFQA, a benchmark designed to evaluate the ability of LLMs to generate long-form answers to complex financial questions with reliable and nuanced attributions. FinLFQA evaluates three critical aspects of attribution through human annotations: (1) supporting evidence extracted from financial reports, (2) intermediate numerical reasoning steps, and (3) domain-specific financial knowledge that informs the reasoning process. We further provide an automatic evaluation framework covering both answer quality and attribution quality. Through extensive experiments on eight LLMs across multiple attribution-generation paradigms, we find that fine-grained metrics are important to distinguish model capabilities, that end-to-end generation achieves comparable performance to post-hoc approaches, and that iterative refinement only helps when guided by external feedback.

Financial dialogue transcripts pose a unique challenge for sentence-level information extraction due to their informal structure, domain-specific vocabulary, and variable intent density. We introduce Fin-ExBERT, a lightweight and modular framework for extracting user intent-relevant sentences from annotated financial service calls. Our approach builds on a domain-adapted BERT (Bidirectional Encoder Representations from Transformers) backbone enhanced with LoRA (Low-Rank Adaptation) adapters, enabling efficient fine-tuning using limited labeled data. We propose a two-stage training strategy with progressive unfreezing: initially training a classifier head while freezing the backbone, followed by gradual fine-tuning of the entire model with differential learning rates. To ensure robust extraction under uncertainty, we adopt a dynamic thresholding strategy based on probability curvature (elbow detection), avoiding fixed cutoff heuristics. Empirical results show strong precision and F1 performance on real-world transcripts, with interpretable output suitable for downstream auditing and question-answering workflows. The full framework supports batched evaluation, visualization, and calibrated export, offering a deployable solution for financial dialogue mining.

This study evaluates deep neural networks for forecasting probability distributions of financial returns. 1D convolutional neural networks (CNN) and Long Short-Term Memory (LSTM) architectures are used to forecast parameters of three probability distributions: Normal, Student's t, and skewed Student's t. Using custom negative log-likelihood loss functions, distribution parameters are optimized directly. The models are tested on six major equity indices (S\&P 500, BOVESPA, DAX, WIG, Nikkei 225, and KOSPI) using probabilistic evaluation metrics including Log Predictive Score (LPS), Continuous Ranked Probability Score (CRPS), and Probability Integral Transform (PIT). Results show that deep learning models provide accurate distributional forecasts and perform competitively with classical GARCH models for Value-at-Risk estimation. The LSTM with skewed Student's t distribution performs best across multiple evaluation criteria, capturing both heavy tails and asymmetry in financial returns. This work shows that deep neural networks are viable alternatives to traditional econometric models for financial risk assessment and portfolio management.

With growing credit card transaction volumes, the fraud percentages are also rising, including overhead costs for institutions to combat and compensate victims. The use of machine learning into the financial sector permits more effective protection against fraud and other economic crime. Suitably trained machine learning classifiers help proactive fraud detection, improving stakeholder trust and robustness against illicit transactions. However, the design of machine learning based fraud detection algorithms has been challenging and slow due the massively unbalanced nature of fraud data and the challenges of identifying the frauds accurately and completely to create a gold standard ground truth. Furthermore, there are no benchmarks or standard classifier evaluation metrics to measure and identify better performing classifiers, thus keeping researchers in the dark. In this work, we develop a theoretical foundation to model human annotation errors and extreme imbalance typical in real world fraud detection data sets. By conducting empirical experiments on a hypothetical classifier, with a synthetic data distribution approximated to a popular real world credit card fraud data set, we simulate human annotation errors and extreme imbalance to observe the behavior of popular machine learning classifier evaluation matrices. We demonstrate that a combined F1 score and g-mean, in that specific order, is the best evaluation metric for typical imbalanced fraud detection model classification.

While LLMs have shown great success in financial tasks like stock prediction and question answering, their application in fully automating Equity Research Report generation remains uncharted territory. In this paper, we formulate the Equity Research Report (ERR) Generation task for the first time. To address the data scarcity and the evaluation metrics absence, we present an open-source evaluation benchmark for ERR generation - FinRpt. We frame a Dataset Construction Pipeline that integrates 7 financial data types and produces a high-quality ERR dataset automatically, which could be used for model training and evaluation. We also introduce a comprehensive evaluation system including 11 metrics to assess the generated ERRs. Moreover, we propose a multi-agent framework specifically tailored to address this task, named FinRpt-Gen, and train several LLM-based agents on the proposed datasets using Supervised Fine-Tuning and Reinforcement Learning. Experimental results indicate the data quality and metrics effectiveness of the benchmark FinRpt and the strong performance of FinRpt-Gen, showcasing their potential to drive innovation in the ERR generation field. All code and datasets are publicly available.

Formula alpha mining, which generates predictive signals from financial data, is critical for quantitative investment. Although various algorithmic approaches-such as genetic programming, reinforcement learning, and large language models-have significantly expanded the capacity for alpha discovery, systematic evaluation remains a key challenge. Existing evaluation metrics predominantly include backtesting and correlation-based measures. Backtesting is computationally intensive, inherently sequential, and sensitive to specific strategy parameters. Correlation-based metrics, though efficient, assess only predictive ability and overlook other crucial properties such as temporal stability, robustness, diversity, and interpretability. Additionally, the closed-source nature of most existing alpha mining models hinders reproducibility and slows progress in this field. To address these issues, we propose AlphaEval, a unified, parallelizable, and backtest-free evaluation framework for automated alpha mining models. AlphaEval assesses the overall quality of generated alphas along five complementary dimensions: predictive power, stability, robustness to market perturbations, financial logic, and diversity. Extensive experiments across representative alpha mining algorithms demonstrate that AlphaEval achieves evaluation consistency comparable to comprehensive backtesting, while providing more comprehensive insights and higher efficiency. Furthermore, AlphaEval effectively identifies superior alphas compared to traditional single-metric screening approaches. All implementations and evaluation tools are open-sourced to promote reproducibility and community engagement.

Financial forecasting has been an important and active area of machine learning research because of the challenges it presents and the potential rewards that even minor improvements in prediction accuracy or forecasting may entail. Traditionally, financial forecasting has heavily relied on quantitative indicators and metrics derived from structured financial statements. Earnings conference call data, including text and audio, is an important source of unstructured data that has been used for various prediction tasks using deep earning and related approaches. However, current deep learning-based methods are limited in the way that they deal with numeric data; numbers are typically treated as plain-text tokens without taking advantage of their underlying numeric structure. This paper describes a numeric-oriented hierarchical transformer model to predict stock returns, and financial risk using multi-modal aligned earnings calls data by taking advantage of the different categories of numbers (monetary, temporal, percentages etc.) and their magnitude. We present the results of a comprehensive evaluation of NumHTML against several state-of-the-art baselines using a real-world publicly available dataset. The results indicate that NumHTML significantly outperforms the current state-of-the-art across a variety of evaluation metrics and that it has the potential to offer significant financial gains in a practical trading context.

The increasing context length of modern language models has created a need for evaluating their ability to retrieve and process information across extensive documents. While existing benchmarks test long-context capabilities, they often lack a structured way to systematically vary question complexity. We introduce KG-QAGen (Knowledge-Graph-based Question-Answer Generation), a framework that (1) extracts QA pairs at multiple complexity levels (2) by leveraging structured representations of financial agreements (3) along three key dimensions -- multi-hop retrieval, set operations, and answer plurality -- enabling fine-grained assessment of model performance across controlled difficulty levels. Using this framework, we construct a dataset of 20,139 QA pairs (the largest number among the long-context benchmarks) and open-source a part of it. We evaluate 13 proprietary and open-source LLMs and observe that even the best-performing models are struggling with set-based comparisons and multi-hop logical inference. Our analysis reveals systematic failure modes tied to semantic misinterpretation and inability to handle implicit relations.

We introduce FinTral, a suite of state-of-the-art multimodal large language models (LLMs) built upon the Mistral-7b model and tailored for financial analysis. FinTral integrates textual, numerical, tabular, and image data. We enhance FinTral with domain-specific pretraining, instruction fine-tuning, and RLAIF training by exploiting a large collection of textual and visual datasets we curate for this work. We also introduce an extensive benchmark featuring nine tasks and 25 datasets for evaluation, including hallucinations in the financial domain. Our FinTral model trained with direct preference optimization employing advanced Tools and Retrieval methods, dubbed FinTral-DPO-T&R, demonstrates an exceptional zero-shot performance. It outperforms ChatGPT-3.5 in all tasks and surpasses GPT-4 in five out of nine tasks, marking a significant advancement in AI-driven financial technology. We also demonstrate that FinTral has the potential to excel in real-time analysis and decision-making in diverse financial contexts.

Stock movement prediction, a fundamental task in financial time-series forecasting, requires identifying and retrieving critical influencing factors from vast amounts of time-series data. However, existing text-trained or numeric similarity-based retrieval methods fall short in handling complex financial analysis. To address this, we propose the first retrieval-augmented generation (RAG) framework for financial time-series forecasting, featuring three key innovations: a fine-tuned 1B parameter large language model (StockLLM) as the backbone, a novel candidate selection method leveraging LLM feedback, and a training objective that maximizes similarity between queries and historically significant sequences. This enables our retriever, FinSeer, to uncover meaningful patterns while minimizing noise in complex financial data. We also construct new datasets integrating financial indicators and historical stock prices to train FinSeer and ensure robust evaluation. Experimental results demonstrate that our RAG framework outperforms bare StockLLM and random retrieval, highlighting its effectiveness, while FinSeer surpasses existing retrieval methods, achieving an 8\% higher accuracy on BIGDATA22 and retrieving more impactful sequences. This work underscores the importance of tailored retrieval models in financial forecasting and provides a novel framework for future research.

Reasoning large language models are rapidly evolving across various domains. However, their capabilities in handling complex financial tasks still require in-depth exploration. In this paper, we introduce Fin-R1, a reasoning large language model specifically designed for the financial sector. Fin-R1 is built using a two-stage architecture, leveraging a financial reasoning dataset distilled and processed based on DeepSeek-R1. Through supervised fine-tuning (SFT) and reinforcement learning (RL) training, it demonstrates performance close to DeepSeek-R1 with a parameter size of 7 billion across a range of financial reasoning tasks. It achieves the state-of-the-art (SOTA) in the FinQA and ConvFinQA tasks between those LLMs in our evaluation, surpassing larger models in other tasks as well. Fin-R1 showcases strong reasoning and decision-making capabilities, providing solutions to various problems encountered in the financial domain. Our code is available at https://github.com/SUFE-AIFLM-Lab/Fin-R1.

Domain-adaptive post-training of large language models (LLMs) has emerged as a promising approach for specialized domains such as medicine and finance. However, significant challenges remain in identifying optimal adaptation criteria and training strategies across varying data and model configurations. To address these challenges, we introduce FINDAP, a systematic and fine-grained investigation into domain-adaptive post-training of LLMs for the finance domain. Our approach begins by identifying the core capabilities required for the target domain and designing a comprehensive evaluation suite aligned with these needs. We then analyze the effectiveness of key post-training stages, including continual pretraining, instruction tuning, and preference alignment. Building on these insights, we propose an effective training recipe centered on a novel preference data distillation method, which leverages process signals from a generative reward model. The resulting model, Llama-Fin, achieves state-of-the-art performance across a wide range of financial tasks. Our analysis also highlights how each post-training stage contributes to distinct capabilities, uncovering specific challenges and effective solutions, providing valuable insights for domain adaptation of LLMs. Project page: https://github.com/SalesforceAIResearch/FinDap

Financial sentiment analysis plays a crucial role in decoding market trends and guiding strategic trading decisions. Despite the deployment of advanced deep learning techniques and language models to refine sentiment analysis in finance, this study breaks new ground by investigating the potential of large language models, particularly ChatGPT 3.5, in financial sentiment analysis, with a strong emphasis on the foreign exchange market (forex). Employing a zero-shot prompting approach, we examine multiple ChatGPT prompts on a meticulously curated dataset of forex-related news headlines, measuring performance using metrics such as precision, recall, f1-score, and Mean Absolute Error (MAE) of the sentiment class. Additionally, we probe the correlation between predicted sentiment and market returns as an additional evaluation approach. ChatGPT, compared to FinBERT, a well-established sentiment analysis model for financial texts, exhibited approximately 35\% enhanced performance in sentiment classification and a 36\% higher correlation with market returns. By underlining the significance of prompt engineering, particularly in zero-shot contexts, this study spotlights ChatGPT's potential to substantially boost sentiment analysis in financial applications. By sharing the utilized dataset, our intention is to stimulate further research and advancements in the field of financial services.

Multi-hop reasoning over financial disclosures is often a retrieval problem before it becomes a reasoning or generation problem: relevant facts are dispersed across sections, filings, companies, and years, and LLMs often expend excessive tokens navigating noisy context. Without precise Knowledge Graph (KG)-guided selection of relevant context, even strong reasoning models either fail to answer or consume excessive tokens, whereas KG-linked evidence enables models to focus their reasoning on composing already retrieved facts. We present FinReflectKG - MultiHop, a benchmark built on FinReflectKG, a temporally indexed financial KG that links audited triples to source chunks from S&P 100 filings (2022-2024). Mining frequent 2-3 hop subgraph patterns across sectors (via GICS taxonomy), we generate financial analyst style questions with exact supporting evidence from the KG. A two-phase pipeline first creates QA pairs via pattern-specific prompts, followed by a multi-criteria quality control evaluation to ensure QA validity. We then evaluate three controlled retrieval scenarios: (S1) precise KG-linked paths; (S2) text-only page windows centered on relevant text spans; and (S3) relevant page windows with randomizations and distractors. Across both reasoning and non-reasoning models, KG-guided precise retrieval yields substantial gains on the FinReflectKG - MultiHop QA benchmark dataset, boosting correctness scores by approximately 24 percent while reducing token utilization by approximately 84.5 percent compared to the page window setting, which reflects the traditional vector retrieval paradigm. Spanning intra-document, inter-year, and cross-company scopes, our work underscores the pivotal role of knowledge graphs in efficiently connecting evidence for multi-hop financial QA. We also release a curated subset of the benchmark (555 QA Pairs) to catalyze further research.

Financial analysis presents complex challenges that could leverage large language model (LLM) capabilities. However, the scarcity of challenging financial datasets, particularly for Japanese financial data, impedes academic innovation in financial analytics. As LLMs advance, this lack of accessible research resources increasingly hinders their development and evaluation in this specialized domain. To address this gap, we introduce EDINET-Bench, an open-source Japanese financial benchmark designed to evaluate the performance of LLMs on challenging financial tasks including accounting fraud detection, earnings forecasting, and industry prediction. EDINET-Bench is constructed by downloading annual reports from the past 10 years from Japan's Electronic Disclosure for Investors' NETwork (EDINET) and automatically assigning labels corresponding to each evaluation task. Our experiments reveal that even state-of-the-art LLMs struggle, performing only slightly better than logistic regression in binary classification for fraud detection and earnings forecasting. These results highlight significant challenges in applying LLMs to real-world financial applications and underscore the need for domain-specific adaptation. Our dataset, benchmark construction code, and evaluation code is publicly available to facilitate future research in finance with LLMs.

We introduce FinanceReasoning, a novel benchmark designed to evaluate the reasoning capabilities of large reasoning models (LRMs) in financial numerical reasoning problems. Compared to existing benchmarks, our work provides three key advancements. (1) Credibility: We update 15.6% of the questions from four public datasets, annotating 908 new questions with detailed Python solutions and rigorously refining evaluation standards. This enables an accurate assessment of the reasoning improvements of LRMs. (2) Comprehensiveness: FinanceReasoning covers 67.8% of financial concepts and formulas, significantly surpassing existing datasets. Additionally, we construct 3,133 Python-formatted functions, which enhances LRMs' financial reasoning capabilities through refined knowledge (e.g., 83.2% rightarrow 91.6% for GPT-4o). (3) Challenge: Models are required to apply multiple financial formulas for precise numerical reasoning on 238 Hard problems. The best-performing model (i.e., OpenAI o1 with PoT) achieves 89.1% accuracy, yet LRMs still face challenges in numerical precision. We demonstrate that combining Reasoner and Programmer models can effectively enhance LRMs' performance (e.g., 83.2% rightarrow 87.8% for DeepSeek-R1). Our work paves the way for future research on evaluating and improving LRMs in domain-specific complex reasoning tasks.

Accurate and transparent financial information disclosure is essential in accounting and finance, fostering trust and enabling informed investment decisions that drive economic development. Among many information disclosure platforms, the Chinese stock exchanges' investor interactive platform provides a novel and interactive way for listed firms to disclose information of interest to investors through an online question-and-answer (Q&A) format. However, it is common for listed firms to respond to questions with limited or no substantive information, and automatically evaluating the quality of financial information disclosure on large amounts of Q&A pairs is challenging. In this study, our interdisciplinary team of AI and finance professionals proposed FinTruthQA, a benchmark designed to evaluate advanced natural language processing (NLP) techniques for the automatic quality assessment of information disclosure in financial Q&A data. It comprises 6,000 real-world financial Q&A entries and each Q&A was manually annotated based on four key evaluation criteria. We benchmarked various NLP techniques on FinTruthQA, including large language models(LLMs). Experiments showed that existing NLP models have strong predictive ability for question identification and question relevance tasks, but are suboptimal for answer readability and answer relevance tasks. By establishing this benchmark, we provide a robust foundation for the automatic evaluation of information disclosure, demonstrating how AI can be leveraged for social good by promoting transparency, fairness, and investor protection in financial disclosure practices. FinTruthQA can be used by auditors, regulators, and financial analysts for real-time monitoring and data-driven decision-making, as well as by researchers for advanced studies in accounting and finance, ultimately fostering greater trust and efficiency in the financial markets.

Text-to-SQL, the task of translating natural language questions into SQL queries, is part of various business processes. Its automation, which is an emerging challenge, will empower software practitioners to seamlessly interact with relational databases using natural language, thereby bridging the gap between business needs and software capabilities. In this paper, we consider Large Language Models (LLMs), which have achieved state of the art for various NLP tasks. Specifically, we benchmark Text-to-SQL performance, the evaluation methodologies, as well as input optimization (e.g., prompting). In light of the empirical observations that we have made, we propose two novel metrics that were designed to adequately measure the similarity between SQL queries. Overall, we share with the community various findings, notably on how to select the right LLM on Text-to-SQL tasks. We further demonstrate that a tree-based edit distance constitutes a reliable metric for assessing the similarity between generated SQL queries and the oracle for benchmarking Text2SQL approaches. This metric is important as it relieves researchers from the need to perform computationally expensive experiments such as executing generated queries as done in prior works. Our work implements financial domain use cases and, therefore contributes to the advancement of Text2SQL systems and their practical adoption in this domain.

To advance Chinese financial natural language processing (NLP), we introduce BBT-FinT5, a new Chinese financial pre-training language model based on the T5 model. To support this effort, we have built BBT-FinCorpus, a large-scale financial corpus with approximately 300GB of raw text from four different sources. In general domain NLP, comprehensive benchmarks like GLUE and SuperGLUE have driven significant advancements in language model pre-training by enabling head-to-head comparisons among models. Drawing inspiration from these benchmarks, we propose BBT-CFLEB, a Chinese Financial Language understanding and generation Evaluation Benchmark, which includes six datasets covering both understanding and generation tasks. Our aim is to facilitate research in the development of NLP within the Chinese financial domain. Our model, corpus and benchmark are released at https://github.com/ssymmetry/BBT-FinCUGE-Applications. Our work belongs to the Big Bang Transformer (BBT), a large-scale pre-trained language model project.

Process Reward Models (PRMs) have emerged as a promising framework for supervising intermediate reasoning in large language models (LLMs), yet existing PRMs are primarily trained on general or Science, Technology, Engineering, and Mathematics (STEM) domains and fall short in domain-specific contexts such as finance, where reasoning is more structured, symbolic, and sensitive to factual and regulatory correctness. We introduce Fin-PRM, a domain-specialized, trajectory-aware PRM tailored to evaluate intermediate reasoning steps in financial tasks. Fin-PRM integrates step-level and trajectory-level reward supervision, enabling fine-grained evaluation of reasoning traces aligned with financial logic. We apply Fin-PRM in both offline and online reward learning settings, supporting three key applications: (i) selecting high-quality reasoning trajectories for distillation-based supervised fine-tuning, (ii) providing dense process-level rewards for reinforcement learning, and (iii) guiding reward-informed Best-of-N inference at test time. Experimental results on financial reasoning benchmarks, including CFLUE and FinQA, demonstrate that Fin-PRM consistently outperforms general-purpose PRMs and strong domain baselines in trajectory selection quality. Downstream models trained with Fin-PRM yield substantial improvements with baselines, with gains of 12.9\% in supervised learning, 5.2\% in reinforcement learning, and 5.1\% in test-time performance. These findings highlight the value of domain-specialized reward modeling for aligning LLMs with expert-level financial reasoning. Our project resources will be available at https://github.com/aliyun/qwen-dianjin.

The rapid advancement of large language models (LLMs) introduces dual-use capabilities that could both threaten and bolster national security and public safety (NSPS). Models implement safeguards to protect against potential misuse relevant to NSPS and allow for benign users to receive helpful information. However, current benchmarks often fail to test safeguard robustness to potential NSPS risks in an objective, robust way. We introduce FORTRESS: 500 expert-crafted adversarial prompts with instance-based rubrics of 4-7 binary questions for automated evaluation across 3 domains (unclassified information only): Chemical, Biological, Radiological, Nuclear and Explosive (CBRNE), Political Violence & Terrorism, and Criminal & Financial Illicit Activities, with 10 total subcategories across these domains. Each prompt-rubric pair has a corresponding benign version to test for model over-refusals. This evaluation of frontier LLMs' safeguard robustness reveals varying trade-offs between potential risks and model usefulness: Claude-3.5-Sonnet demonstrates a low average risk score (ARS) (14.09 out of 100) but the highest over-refusal score (ORS) (21.8 out of 100), while Gemini 2.5 Pro shows low over-refusal (1.4) but a high average potential risk (66.29). Deepseek-R1 has the highest ARS at 78.05, but the lowest ORS at only 0.06. Models such as o1 display a more even trade-off between potential risks and over-refusals (with an ARS of 21.69 and ORS of 5.2). To provide policymakers and researchers with a clear understanding of models' potential risks, we publicly release FORTRESS at https://huggingface.co/datasets/ScaleAI/fortress_public. We also maintain a private set for evaluation.

Retrieval-Augmented Generation (RAG) plays a vital role in the financial domain, powering applications such as real-time market analysis, trend forecasting, and interest rate computation. However, most existing RAG research in finance focuses predominantly on textual data, overlooking the rich visual content in financial documents, resulting in the loss of key analytical insights. To bridge this gap, we present FinRAGBench-V, a comprehensive visual RAG benchmark tailored for finance which effectively integrates multimodal data and provides visual citation to ensure traceability. It includes a bilingual retrieval corpus with 60,780 Chinese and 51,219 English pages, along with a high-quality, human-annotated question-answering (QA) dataset spanning heterogeneous data types and seven question categories. Moreover, we introduce RGenCite, an RAG baseline that seamlessly integrates visual citation with generation. Furthermore, we propose an automatic citation evaluation method to systematically assess the visual citation capabilities of Multimodal Large Language Models (MLLMs). Extensive experiments on RGenCite underscore the challenging nature of FinRAGBench-V, providing valuable insights for the development of multimodal RAG systems in finance.

Domain specificity of embedding models is critical for effective performance. However, existing benchmarks, such as FinMTEB, are primarily designed for high-resource languages, leaving low-resource settings, such as Korean, under-explored. Directly translating established English benchmarks often fails to capture the linguistic and cultural nuances present in low-resource domains. In this paper, titled TWICE: What Advantages Can Low-Resource Domain-Specific Embedding Models Bring? A Case Study on Korea Financial Texts, we introduce KorFinMTEB, a novel benchmark for the Korean financial domain, specifically tailored to reflect its unique cultural characteristics in low-resource languages. Our experimental results reveal that while the models perform robustly on a translated version of FinMTEB, their performance on KorFinMTEB uncovers subtle yet critical discrepancies, especially in tasks requiring deeper semantic understanding, that underscore the limitations of direct translation. This discrepancy highlights the necessity of benchmarks that incorporate language-specific idiosyncrasies and cultural nuances. The insights from our study advocate for the development of domain-specific evaluation frameworks that can more accurately assess and drive the progress of embedding models in low-resource settings.

Large Language Models (LLMs) have stunningly advanced the field of machine translation, though their effectiveness within the financial domain remains largely underexplored. To probe this issue, we constructed a fine-grained Chinese-English parallel corpus of financial news called FFN. We acquired financial news articles spanning between January 1st, 2014, to December 31, 2023, from mainstream media websites such as CNN, FOX, and China Daily. The dataset consists of 1,013 main text and 809 titles, all of which have been manually corrected. We measured the translation quality of two LLMs -- ChatGPT and ERNIE-bot, utilizing BLEU, TER and chrF scores as the evaluation metrics. For comparison, we also trained an OpenNMT model based on our dataset. We detail problems of LLMs and provide in-depth analysis, intending to stimulate further research and solutions in this largely uncharted territory. Our research underlines the need to optimize LLMs within the specific field of financial translation to ensure accuracy and quality.

The global economy is increasingly dependent on knowledge workers to meet the needs of public and private organizations. While there is no single definition of knowledge work, organizations and industry groups still attempt to measure individuals' capability to engage in it. The most comprehensive assessment of capability readiness for professional knowledge workers is the Uniform CPA Examination developed by the American Institute of Certified Public Accountants (AICPA). In this paper, we experimentally evaluate OpenAI's `text-davinci-003` and prior versions of GPT on both a sample Regulation (REG) exam and an assessment of over 200 multiple-choice questions based on the AICPA Blueprints for legal, financial, accounting, technology, and ethical tasks. First, we find that `text-davinci-003` achieves a correct rate of 14.4% on a sample REG exam section, significantly underperforming human capabilities on quantitative reasoning in zero-shot prompts. Second, `text-davinci-003` appears to be approaching human-level performance on the Remembering & Understanding and Application skill levels in the Exam absent calculation. For best prompt and parameters, the model answers 57.6% of questions correctly, significantly better than the 25% guessing rate, and its top two answers are correct 82.1% of the time, indicating strong non-entailment. Finally, we find that recent generations of GPT-3 demonstrate material improvements on this assessment, rising from 30% for `text-davinci-001` to 57% for `text-davinci-003`. These findings strongly suggest that large language models have the potential to transform the quality and efficiency of future knowledge work.

We introduce FinTagging, the first full-scope, table-aware XBRL benchmark designed to evaluate the structured information extraction and semantic alignment capabilities of large language models (LLMs) in the context of XBRL-based financial reporting. Unlike prior benchmarks that oversimplify XBRL tagging as flat multi-class classification and focus solely on narrative text, FinTagging decomposes the XBRL tagging problem into two subtasks: FinNI for financial entity extraction and FinCL for taxonomy-driven concept alignment. It requires models to jointly extract facts and align them with the full 10k+ US-GAAP taxonomy across both unstructured text and structured tables, enabling realistic, fine-grained evaluation. We assess a diverse set of LLMs under zero-shot settings, systematically analyzing their performance on both subtasks and overall tagging accuracy. Our results reveal that, while LLMs demonstrate strong generalization in information extraction, they struggle with fine-grained concept alignment, particularly in disambiguating closely related taxonomy entries. These findings highlight the limitations of existing LLMs in fully automating XBRL tagging and underscore the need for improved semantic reasoning and schema-aware modeling to meet the demands of accurate financial disclosure. Code is available at our GitHub repository and data is at our Hugging Face repository.

As large language models become increasingly prevalent in the financial sector, there is a pressing need for a standardized method to comprehensively assess their performance. However, existing finance benchmarks often suffer from limited language and task coverage, as well as challenges such as low-quality datasets and inadequate adaptability for LLM evaluation. To address these limitations, we propose "Golden Touchstone", the first comprehensive bilingual benchmark for financial LLMs, which incorporates representative datasets from both Chinese and English across eight core financial NLP tasks. Developed from extensive open source data collection and industry-specific demands, this benchmark includes a variety of financial tasks aimed at thoroughly assessing models' language understanding and generation capabilities. Through comparative analysis of major models on the benchmark, such as GPT-4o Llama3, FinGPT and FinMA, we reveal their strengths and limitations in processing complex financial information. Additionally, we open-sourced Touchstone-GPT, a financial LLM trained through continual pre-training and financial instruction tuning, which demonstrates strong performance on the bilingual benchmark but still has limitations in specific tasks.This research not only provides the financial large language models with a practical evaluation tool but also guides the development and optimization of future research. The source code for Golden Touchstone and model weight of Touchstone-GPT have been made publicly available at https://github.com/IDEA-FinAI/Golden-Touchstone, contributing to the ongoing evolution of FinLLMs and fostering further research in this critical area.

Large Language Models (LLMs) are increasingly being used to simulate human-like decision making in agent-based financial market models (ABMs). As models become more powerful and accessible, researchers can now incorporate individual LLM decisions into ABM environments. However, integration may introduce inherent biases that need careful evaluation. In this paper we test three state-of-the-art GPT models for bias using two model sampling approaches: one-shot and few-shot API queries. We observe significant variations in distributions of outputs between specific models, and model sub versions, with GPT-4o-Mini-2024-07-18 showing notably better performance (32-43% yes responses) compared to GPT-4-0125-preview's extreme bias (98-99% yes responses). We show that sampling methods and model sub-versions significantly impact results: repeated independent API calls produce different distributions compared to batch sampling within a single call. While no current GPT model can simultaneously achieve a uniform distribution and Markovian properties in one-shot testing, few-shot sampling can approach uniform distributions under certain conditions. We explore the Temperature parameter, providing a definition and comparative results. We further compare our results to true random binary series and test specifically for the common human bias of Negative Recency - finding LLMs have a mixed ability to 'beat' humans in this one regard. These findings emphasise the critical importance of careful LLM integration into ABMs for financial markets and more broadly.

We conducted extensive experiments on domain adaptation of the Meta-Llama-3-70B-Instruct model on SEC data, exploring its performance on both general and domain-specific benchmarks. Our focus included continual pre-training (CPT) and model merging, aiming to enhance the model's domain-specific capabilities while mitigating catastrophic forgetting. Through this study, we evaluated the impact of integrating financial regulatory data into a robust language model and examined the effectiveness of our model merging techniques in preserving and improving the model's instructive abilities. The model is accessible at hugging face: https://huggingface.co/arcee-ai/Llama-3-SEC-Base, arcee-ai/Llama-3-SEC-Base. This is an intermediate checkpoint of our final model, which has seen 20B tokens so far. The full model is still in the process of training. This is a preprint technical report with thorough evaluations to understand the entire process.

The introduction of ChatGPT has garnered widespread attention in both academic and industrial communities. ChatGPT is able to respond effectively to a wide range of human questions, providing fluent and comprehensive answers that significantly surpass previous public chatbots in terms of security and usefulness. On one hand, people are curious about how ChatGPT is able to achieve such strength and how far it is from human experts. On the other hand, people are starting to worry about the potential negative impacts that large language models (LLMs) like ChatGPT could have on society, such as fake news, plagiarism, and social security issues. In this work, we collected tens of thousands of comparison responses from both human experts and ChatGPT, with questions ranging from open-domain, financial, medical, legal, and psychological areas. We call the collected dataset the Human ChatGPT Comparison Corpus (HC3). Based on the HC3 dataset, we study the characteristics of ChatGPT's responses, the differences and gaps from human experts, and future directions for LLMs. We conducted comprehensive human evaluations and linguistic analyses of ChatGPT-generated content compared with that of humans, where many interesting results are revealed. After that, we conduct extensive experiments on how to effectively detect whether a certain text is generated by ChatGPT or humans. We build three different detection systems, explore several key factors that influence their effectiveness, and evaluate them in different scenarios. The dataset, code, and models are all publicly available at https://github.com/Hello-SimpleAI/chatgpt-comparison-detection.

Financial analysis is an important tool for evaluating company performance. Practitioners work to answer financial questions to make profitable investment decisions, and use advanced quantitative analyses to do so. As a result, Financial Question Answering (QA) is a question answering task that requires deep reasoning about numbers. Furthermore, it is unknown how well pre-trained language models can reason in the financial domain. The current state-of-the-art requires a retriever to collect relevant facts about the financial question from the text and a generator to produce a valid financial program and a final answer. However, recently large language models like GPT-3 have achieved state-of-the-art performance on wide variety of tasks with just a few shot examples. We run several experiments with GPT-3 and find that a separate retrieval model and logic engine continue to be essential components to achieving SOTA performance in this task, particularly due to the precise nature of financial questions and the complex information stored in financial documents. With this understanding, our refined prompt-engineering approach on GPT-3 achieves near SOTA accuracy without any fine-tuning.

Personalized financial advice requires consideration of user goals, constraints, risk tolerance, and jurisdiction. Prior LLM work has focused on support systems for investors and financial planners. Simultaneously, numerous recent studies examine broader personal finance tasks, including budgeting, debt management, retirement, and estate planning, through agentic pipelines that incur high maintenance costs, yielding less than 25% of their expected financial returns. In this study, we introduce a novel and reproducible framework that integrates relevant financial context with behavioral finance studies to construct supervision data for end-to-end advisors. Using this framework, we create a 19k sample reasoning dataset and conduct a comprehensive fine-tuning of the Qwen-3-8B model on the dataset. Through a held-out test split and a blind LLM-jury study, we demonstrate that through careful data curation and behavioral integration, our 8B model achieves performance comparable to significantly larger baselines (14-32B parameters) across factual accuracy, fluency, and personalization metrics while incurring 80% lower costs than the larger counterparts.

Large language models (LLMs) have demonstrated strong capabilities in language understanding, generation, and reasoning, yet their potential in finance remains underexplored due to the complexity and specialization of financial knowledge. In this work, we report the development of the Baichuan4-Finance series, including a comprehensive suite of foundational Baichuan4-Finance-Base and an aligned language model Baichuan4-Finance, which are built upon Baichuan4-Turbo base model and tailored for finance domain. Firstly, we have dedicated significant effort to building a detailed pipeline for improving data quality. Moreover, in the continual pre-training phase, we propose a novel domain self-constraint training strategy, which enables Baichuan4-Finance-Base to acquire financial knowledge without losing general capabilities. After Supervised Fine-tuning and Reinforcement Learning from Human Feedback and AI Feedback, the chat model Baichuan4-Finance is able to tackle various financial certification questions and real-world scenario applications. We evaluate Baichuan4-Finance on many widely used general datasets and two holistic financial benchmarks. The evaluation results show that Baichuan4-Finance-Base surpasses almost all competitive baselines on financial tasks by significant margins without sacrificing performance on general LLM benchmarks. At the same time, Baichuan4-Finance demonstrates even more impressive performance on financial application scenarios, showcasing its potential to foster community innovation in the financial LLM field.

Traditional Retrieval-Augmented Generation (RAG) pipelines rely on similarity-based retrieval and re-ranking, which depend on heuristics such as top-k, and lack explainability, interpretability, and robustness against adversarial content. To address this gap, we propose a novel method METEORA that replaces re-ranking in RAG with a rationale-driven selection approach. METEORA operates in two stages. First, a general-purpose LLM is preference-tuned to generate rationales conditioned on the input query using direct preference optimization. These rationales guide the evidence chunk selection engine, which selects relevant chunks in three stages: pairing individual rationales with corresponding retrieved chunks for local relevance, global selection with elbow detection for adaptive cutoff, and context expansion via neighboring chunks. This process eliminates the need for top-k heuristics. The rationales are also used for consistency check using a Verifier LLM to detect and filter poisoned or misleading content for safe generation. The framework provides explainable and interpretable evidence flow by using rationales consistently across both selection and verification. Our evaluation across six datasets spanning legal, financial, and academic research domains shows that METEORA improves generation accuracy by 33.34% while using approximately 50% fewer chunks than state-of-the-art re-ranking methods. In adversarial settings, METEORA significantly improves the F1 score from 0.10 to 0.44 over the state-of-the-art perplexity-based defense baseline, demonstrating strong resilience to poisoning attacks. Code available at: https://anonymous.4open.science/r/METEORA-DC46/README.md

Embedding models play a crucial role in representing and retrieving information across various NLP applications. Recent advances in large language models (LLMs) have further enhanced the performance of embedding models. While these models are often benchmarked on general-purpose datasets, real-world applications demand domain-specific evaluation. In this work, we introduce the Finance Massive Text Embedding Benchmark (FinMTEB), a specialized counterpart to MTEB designed for the financial domain. FinMTEB comprises 64 financial domain-specific embedding datasets across 7 tasks that cover diverse textual types in both Chinese and English, such as financial news articles, corporate annual reports, ESG reports, regulatory filings, and earnings call transcripts. We also develop a finance-adapted model, FinPersona-E5, using a persona-based data synthetic method to cover diverse financial embedding tasks for training. Through extensive evaluation of 15 embedding models, including FinPersona-E5, we show three key findings: (1) performance on general-purpose benchmarks shows limited correlation with financial domain tasks; (2) domain-adapted models consistently outperform their general-purpose counterparts; and (3) surprisingly, a simple Bag-of-Words (BoW) approach outperforms sophisticated dense embeddings in financial Semantic Textual Similarity (STS) tasks, underscoring current limitations in dense embedding techniques. Our work establishes a robust evaluation framework for financial NLP applications and provides crucial insights for developing domain-specific embedding models.

In recent years, Large Language Models (LLMs) like ChatGPT have seen considerable advancements and have been applied in diverse fields. Built on the Transformer architecture, these models are trained on extensive datasets, enabling them to understand and generate human language effectively. In the financial domain, the deployment of LLMs is gaining momentum. These models are being utilized for automating financial report generation, forecasting market trends, analyzing investor sentiment, and offering personalized financial advice. Leveraging their natural language processing capabilities, LLMs can distill key insights from vast financial data, aiding institutions in making informed investment choices and enhancing both operational efficiency and customer satisfaction. In this study, we provide a comprehensive overview of the emerging integration of LLMs into various financial tasks. Additionally, we conducted holistic tests on multiple financial tasks through the combination of natural language instructions. Our findings show that GPT-4 effectively follow prompt instructions across various financial tasks. This survey and evaluation of LLMs in the financial domain aim to deepen the understanding of LLMs' current role in finance for both financial practitioners and LLM researchers, identify new research and application prospects, and highlight how these technologies can be leveraged to solve practical challenges in the finance industry.

Non-Fungible Tokens (NFTs) represent deeds of ownership, based on blockchain technologies and smart contracts, of unique crypto assets on digital art forms (e.g., artworks or collectibles). In the spotlight after skyrocketing in 2021, NFTs have attracted the attention of crypto enthusiasts and investors intent on placing promising investments in this profitable market. However, the NFT financial performance prediction has not been widely explored to date. In this work, we address the above problem based on the hypothesis that NFT images and their textual descriptions are essential proxies to predict the NFT selling prices. To this purpose, we propose MERLIN, a novel multimodal deep learning framework designed to train Transformer-based language and visual models, along with graph neural network models, on collections of NFTs' images and texts. A key aspect in MERLIN is its independence on financial features, as it exploits only the primary data a user interested in NFT trading would like to deal with, i.e., NFT images and textual descriptions. By learning dense representations of such data, a price-category classification task is performed by MERLIN models, which can also be tuned according to user preferences in the inference phase to mimic different risk-return investment profiles. Experimental evaluation on a publicly available dataset has shown that MERLIN models achieve significant performances according to several financial assessment criteria, fostering profitable investments, and also beating baseline machine-learning classifiers based on financial features.

Large language models (LLMs) cannot be trusted for economic forecasts during periods covered by their training data. We provide the first systematic evaluation of LLMs' memorization of economic and financial data, including major economic indicators, news headlines, stock returns, and conference calls. Our findings show that LLMs can perfectly recall the exact numerical values of key economic variables from before their knowledge cutoff dates. This recall appears to be randomly distributed across different dates and data types. This selective perfect memory creates a fundamental issue -- when testing forecasting capabilities before their knowledge cutoff dates, we cannot distinguish whether LLMs are forecasting or simply accessing memorized data. Explicit instructions to respect historical data boundaries fail to prevent LLMs from achieving recall-level accuracy in forecasting tasks. Further, LLMs seem exceptional at reconstructing masked entities from minimal contextual clues, suggesting that masking provides inadequate protection against motivated reasoning. Our findings raise concerns about using LLMs to forecast historical data or backtest trading strategies, as their apparent predictive success may merely reflect memorization rather than genuine economic insight. Any application where future knowledge would change LLMs' outputs can be affected by memorization. In contrast, consistent with the absence of data contamination, LLMs cannot recall data after their knowledge cutoff date.

Traditional Long Short-Term Memory (LSTM) networks are effective for handling sequential data but have limitations such as gradient vanishing and difficulty in capturing long-term dependencies, which can impact their performance in dynamic and risky environments like stock trading. To address these limitations, this study explores the usage of the newly introduced Extended Long Short Term Memory (xLSTM) network in combination with a deep reinforcement learning (DRL) approach for automated stock trading. Our proposed method utilizes xLSTM networks in both actor and critic components, enabling effective handling of time series data and dynamic market environments. Proximal Policy Optimization (PPO), with its ability to balance exploration and exploitation, is employed to optimize the trading strategy. Experiments were conducted using financial data from major tech companies over a comprehensive timeline, demonstrating that the xLSTM-based model outperforms LSTM-based methods in key trading evaluation metrics, including cumulative return, average profitability per trade, maximum earning rate, maximum pullback, and Sharpe ratio. These findings mark the potential of xLSTM for enhancing DRL-based stock trading systems.

In financial trading, large language model (LLM)-based agents demonstrate significant potential. However, the high sensitivity to market noise undermines the performance of LLM-based trading systems. To address this limitation, we propose a novel multi-agent system featuring an internal competitive mechanism inspired by modern corporate management structures. The system consists of two specialized teams: (1) Data Team - responsible for processing and condensing massive market data into diversified text factors, ensuring they fit the model's constrained context. (2) Research Team - tasked with making parallelized multipath trading decisions based on deep research methods. The core innovation lies in implementing a real-time evaluation and ranking mechanism within each team, driven by authentic market feedback. Each agent's performance undergoes continuous scoring and ranking, with only outputs from top-performing agents being adopted. The design enables the system to adaptively adjust to dynamic environment, enhances robustness against market noise and ultimately delivers superior trading performance. Experimental results demonstrate that our proposed system significantly outperforms prevailing multi-agent systems and traditional quantitative investment methods across diverse evaluation metrics. ContestTrade is open-sourced on GitHub at https://github.com/FinStep-AI/ContestTrade.

Financial asset recommendation (FAR) is a sub-domain of recommender systems which identifies useful financial securities for investors, with the expectation that they will invest capital on the recommended assets. FAR solutions analyse and learn from multiple data sources, including time series pricing data, customer profile information and expectations, as well as past investments. However, most models have been developed over proprietary datasets, making a comparison over a common benchmark impossible. In this paper, we aim to solve this problem by introducing FAR-Trans, the first public dataset for FAR, containing pricing information and retail investor transactions acquired from a large European financial institution. We also provide a bench-marking comparison between eleven FAR algorithms over the data for use as future baselines. The dataset can be downloaded from https://doi.org/10.5525/gla.researchdata.1658 .

Annual Reports of publicly listed companies contain vital information about their financial health which can help assess the potential impact on Stock price of the firm. These reports are comprehensive in nature, going up to, and sometimes exceeding, 100 pages. Analysing these reports is cumbersome even for a single firm, let alone the whole universe of firms that exist. Over the years, financial experts have become proficient in extracting valuable information from these documents relatively quickly. However, this requires years of practice and experience. This paper aims to simplify the process of assessing Annual Reports of all the firms by leveraging the capabilities of Large Language Models (LLMs). The insights generated by the LLM are compiled in a Quant styled dataset and augmented by historical stock price data. A Machine Learning model is then trained with LLM outputs as features. The walkforward test results show promising outperformance wrt S&P500 returns. This paper intends to provide a framework for future work in this direction. To facilitate this, the code has been released as open source.

Standard Full-Data classifiers in NLP demand thousands of labeled examples, which is impractical in data-limited domains. Few-shot methods offer an alternative, utilizing contrastive learning techniques that can be effective with as little as 20 examples per class. Similarly, Large Language Models (LLMs) like GPT-4 can perform effectively with just 1-5 examples per class. However, the performance-cost trade-offs of these methods remain underexplored, a critical concern for budget-limited organizations. Our work addresses this gap by studying the aforementioned approaches over the Banking77 financial intent detection dataset, including the evaluation of cutting-edge LLMs by OpenAI, Cohere, and Anthropic in a comprehensive set of few-shot scenarios. We complete the picture with two additional methods: first, a cost-effective querying method for LLMs based on retrieval-augmented generation (RAG), able to reduce operational costs multiple times compared to classic few-shot approaches, and second, a data augmentation method using GPT-4, able to improve performance in data-limited scenarios. Finally, to inspire future research, we provide a human expert's curated subset of Banking77, along with extensive error analysis.

Over the past decade, tremendous progress has been made in Recommender Systems (RecSys) for well-known tasks such as next-item and next-basket prediction. On the other hand, the recently proposed next-period recommendation (NPR) task is not covered as much. Current works about NPR are mostly based around distinct problem formulations, methods, and proprietary datasets, making solutions difficult to reproduce. In this article, we aim to fill the gap in RecSys methods evaluation on the NPR task using publicly available datasets and (1) introduce the TTRS, a large-scale financial transactions dataset suitable for RecSys methods evaluation; (2) benchmark popular RecSys approaches on several datasets for the NPR task. When performing our analysis, we found a strong repetitive consumption pattern in several real-world datasets. With this setup, our results suggest that the repetitive nature of data is still hard to generalize for the evaluated RecSys methods, and novel item prediction performance is still questionable.

Regulatory documents, issued by governmental regulatory bodies, establish rules, guidelines, and standards that organizations must adhere to for legal compliance. These documents, characterized by their length, complexity and frequent updates, are challenging to interpret, requiring significant allocation of time and expertise on the part of organizations to ensure ongoing compliance.Regulatory Natural Language Processing (RegNLP) is a multidisciplinary subfield aimed at simplifying access to and interpretation of regulatory rules and obligations. We define an Automated Question-Passage Generation task for RegNLP, create the ObliQA dataset containing 27,869 questions derived from the Abu Dhabi Global Markets (ADGM) financial regulation document collection, design a baseline Regulatory Information Retrieval and Answer Generation system, and evaluate it with RePASs, a novel evaluation metric that tests whether generated answers accurately capture all relevant obligations and avoid contradictions.

We present initial results of a forthcoming benchmark for evaluating LLM agents on white-collar tasks of economic value. We evaluate agents on real-world "messy" open-web research tasks of the type that are routine in finance and consulting. In doing so, we lay the groundwork for an LLM agent evaluation suite where good performance directly corresponds to a large economic and societal impact. We built and tested several agent architectures with o1-preview, GPT-4o, Claude-3.5 Sonnet, Llama 3.1 (405b), and GPT-4o-mini. On average, LLM agents powered by Claude-3.5 Sonnet and o1-preview substantially outperformed agents using GPT-4o, with agents based on Llama 3.1 (405b) and GPT-4o-mini lagging noticeably behind. Across LLMs, a ReAct architecture with the ability to delegate subtasks to subagents performed best. In addition to quantitative evaluations, we qualitatively assessed the performance of the LLM agents by inspecting their traces and reflecting on their observations. Our evaluation represents the first in-depth assessment of agents' abilities to conduct challenging, economically valuable analyst-style research on the real open web.

The financial industry's growing demand for advanced natural language processing (NLP) capabilities has highlighted the limitations of generalist large language models (LLMs) in handling domain-specific financial tasks. To address this gap, we introduce the LLM Pro Finance Suite, a collection of five instruction-tuned LLMs (ranging from 8B to 70B parameters) specifically designed for financial applications. Our approach focuses on enhancing generalist instruction-tuned models, leveraging their existing strengths in instruction following, reasoning, and toxicity control, while fine-tuning them on a curated, high-quality financial corpus comprising over 50% finance-related data in English, French, and German. We evaluate the LLM Pro Finance Suite on a comprehensive financial benchmark suite, demonstrating consistent improvement over state-of-the-art baselines in finance-oriented tasks and financial translation. Notably, our models maintain the strong general-domain capabilities of their base models, ensuring reliable performance across non-specialized tasks. This dual proficiency, enhanced financial expertise without compromise on general abilities, makes the LLM Pro Finance Suite an ideal drop-in replacement for existing LLMs in financial workflows, offering improved domain-specific performance while preserving overall versatility. We publicly release two 8B-parameters models to foster future research and development in financial NLP applications: https://huggingface.co/collections/DragonLLM/llm-open-finance.

Frontier model progress is often measured by academic benchmarks, which offer a limited view of performance in real-world professional contexts. Existing evaluations often fail to assess open-ended, economically consequential tasks in high-stakes domains like Legal and Finance, where practical returns are paramount. To address this, we introduce Professional Reasoning Bench (PRBench), a realistic, open-ended, and difficult benchmark of real-world problems in Finance and Law. We open-source its 1,100 expert-authored tasks and 19,356 expert-curated criteria, making it, to our knowledge, the largest public, rubric-based benchmark for both legal and finance domains. We recruit 182 qualified professionals, holding JDs, CFAs, or 6+ years of experience, who contributed tasks inspired by their actual workflows. This process yields significant diversity, with tasks spanning 114 countries and 47 US jurisdictions. Our expert-curated rubrics are validated through a rigorous quality pipeline, including independent expert validation. Subsequent evaluation of 20 leading models reveals substantial room for improvement, with top scores of only 0.39 (Finance) and 0.37 (Legal) on our Hard subsets. We further catalog associated economic impacts of the prompts and analyze performance using human-annotated rubric categories. Our analysis shows that models with similar overall scores can diverge significantly on specific capabilities. Common failure modes include inaccurate judgments, a lack of process transparency and incomplete reasoning, highlighting critical gaps in their reliability for professional adoption.

This research presents a framework for quantitative risk management in volatile markets, specifically focusing on expectile-based methodologies applied to the FTSE 100 index. Traditional risk measures such as Value-at-Risk (VaR) have demonstrated significant limitations during periods of market stress, as evidenced during the 2008 financial crisis and subsequent volatile periods. This study develops an advanced expectile-based framework that addresses the shortcomings of conventional quantile-based approaches by providing greater sensitivity to tail losses and improved stability in extreme market conditions. The research employs a dataset spanning two decades of FTSE 100 returns, incorporating periods of high volatility, market crashes, and recovery phases. Our methodology introduces novel mathematical formulations for expectile regression models, enhanced threshold determination techniques using time series analysis, and robust backtesting procedures. The empirical results demonstrate that expectile-based Value-at-Risk (EVaR) consistently outperforms traditional VaR measures across various confidence levels and market conditions. The framework exhibits superior performance during volatile periods, with reduced model risk and enhanced predictive accuracy. Furthermore, the study establishes practical implementation guidelines for financial institutions and provides evidence-based recommendations for regulatory compliance and portfolio management. The findings contribute significantly to the literature on financial risk management and offer practical tools for practitioners dealing with volatile market environments.

FinanceBench is a first-of-its-kind test suite for evaluating the performance of LLMs on open book financial question answering (QA). It comprises 10,231 questions about publicly traded companies, with corresponding answers and evidence strings. The questions in FinanceBench are ecologically valid and cover a diverse set of scenarios. They are intended to be clear-cut and straightforward to answer to serve as a minimum performance standard. We test 16 state of the art model configurations (including GPT-4-Turbo, Llama2 and Claude2, with vector stores and long context prompts) on a sample of 150 cases from FinanceBench, and manually review their answers (n=2,400). The cases are available open-source. We show that existing LLMs have clear limitations for financial QA. Notably, GPT-4-Turbo used with a retrieval system incorrectly answered or refused to answer 81% of questions. While augmentation techniques such as using longer context window to feed in relevant evidence improve performance, they are unrealistic for enterprise settings due to increased latency and cannot support larger financial documents. We find that all models examined exhibit weaknesses, such as hallucinations, that limit their suitability for use by enterprises.

The Russian Financial Statements Database (RFSD) is an open, harmonized collection of annual unconsolidated financial statements of the universe of Russian firms in 2011-2023. It is the first open data set with information on every active firm in the country, including non-filing firms. With 56.6 million geolocated firm-year observations gathered from two official sources, the RFSD features multiple end-user quality-of-life improvements such as data imputation, statement articulation, harmonization across data providers and formats, and data enrichment. Extensive internal and external validation shows that most statements articulate well while their aggregates display higher correlation with the regional GDP than the previous gridded GDP data products. We also examine the direction and magnitude of the reporting bias by comparing the universe of firms that are required to file with the actual filers. The RFSD can be used in various economic applications as diverse as calibration of micro-founded models, estimation of markups and productivity, or assessing industry organization and market power.

Answering questions within business and finance requires reasoning, precision, and a wide-breadth of technical knowledge. Together, these requirements make this domain difficult for large language models (LLMs). We introduce BizBench, a benchmark for evaluating models' ability to reason about realistic financial problems. BizBench comprises eight quantitative reasoning tasks, focusing on question-answering (QA) over financial data via program synthesis. We include three financially-themed code-generation tasks from newly collected and augmented QA data. Additionally, we isolate the reasoning capabilities required for financial QA: reading comprehension of financial text and tables for extracting intermediate values, and understanding financial concepts and formulas needed to calculate complex solutions. Collectively, these tasks evaluate a model's financial background knowledge, ability to parse financial documents, and capacity to solve problems with code. We conduct an in-depth evaluation of open-source and commercial LLMs, comparing and contrasting the behavior of code-focused and language-focused models. We demonstrate that the current bottleneck in performance is due to LLMs' limited business and financial understanding, highlighting the value of a challenging benchmark for quantitative reasoning within this domain.

Large language models (LLMs) have demonstrated great potential in the financial domain. Thus, it becomes important to assess the performance of LLMs in the financial tasks. In this work, we introduce CFBenchmark, to evaluate the performance of LLMs for Chinese financial assistant. The basic version of CFBenchmark is designed to evaluate the basic ability in Chinese financial text processing from three aspects~(i.e. recognition, classification, and generation) including eight tasks, and includes financial texts ranging in length from 50 to over 1,800 characters. We conduct experiments on several LLMs available in the literature with CFBenchmark-Basic, and the experimental results indicate that while some LLMs show outstanding performance in specific tasks, overall, there is still significant room for improvement in basic tasks of financial text processing with existing models. In the future, we plan to explore the advanced version of CFBenchmark, aiming to further explore the extensive capabilities of language models in more profound dimensions as a financial assistant in Chinese. Our codes are released at https://github.com/TongjiFinLab/CFBenchmark.

Large Language Models (LLMs) have demonstrated impressive capabilities across various domains, but their effectiveness in financial decision-making remains inadequately evaluated. Current benchmarks primarily assess LLMs' understanding on financial documents rather than the ability to manage assets or dig out trading opportunities in dynamic market conditions. Despite the release of new benchmarks for evaluating diversified tasks on the financial domain, we identified four major problems in these benchmarks, which are data leakage, navel-gazing, over-intervention, and maintenance-hard. To pave the research gap, we introduce DeepFund, a comprehensive arena platform for evaluating LLM-based trading strategies in a live environment. Our approach implements a multi-agent framework where they serve as multiple key roles that realize the real-world investment decision processes. Moreover, we provide a web interface that visualizes LLMs' performance with fund investment metrics across different market conditions, enabling detailed comparative analysis. Through DeepFund, we aim to provide a more realistic and fair assessment on LLM's capabilities in fund investment, offering diversified insights and revealing their potential applications in real-world financial markets. Our code is publicly available at https://github.com/HKUSTDial/DeepFund.