2 papers
cs.CL2026
TRE: Encouraging Exploration in the Trust Region
Chao Huang, Yujing Lu, Quangang Li +8
Entropy regularization is a standard technique in reinforcement learning (RL) to enhance exploration, yet it yields negligible effects or even degrades performance in Large Languag…
cs.CR2025
Safety Alignment Should Be Made More Than Just A Few Attention Heads
Chao Huang, Zefeng Zhang, Juewei Yue +3
Current safety alignment for large language models(LLMs) continues to present vulnerabilities, given that adversarial prompting can effectively bypass their safety measures.Our inv…