Youliang Yuan

Youliang's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored 2 papers over 1 year ago

GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher

Paper • 2308.06463 • Published Aug 12, 2023 • 1

Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training

Paper • 2407.09121 • Published Jul 12, 2024 • 6