4 papers
Large Reasoning Models Learn Better Alignment from Flawed Thinking
ShengYun Peng, Eric Smith, Ivan Evtimov +7
Large reasoning models (LRMs) "think" by generating structured chain-of-thought (CoT) before producing a final answer, yet they still lack the ability to reason critically about sa…
Shape it Up! Restoring LLM Safety during Finetuning
ShengYun Peng, Pin-Yu Chen, Jianfeng Chi +2
Finetuning large language models (LLMs) enables user-specific customization but introduces critical safety risks: even a few harmful examples can compromise safety alignment. A com…
Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety
Seongmin Lee, Aeree Cho, Grace C. Kim +3
As large language models (LLMs) see wider real-world use, understanding and mitigating their unsafe behaviors is critical. Interpretation techniques can reveal causes of unsafe out…
Navigating the Safety Landscape: Measuring Risks in Finetuning Large Language Models
ShengYun Peng, Pin-Yu Chen, Matthew Hull +1
Safety alignment is crucial to ensure that large language models (LLMs) behave in ways that align with human preferences and prevent harmful actions during inference. However, rece…