Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
RAPO: Risk-Aware Preference Optimization for Generalizable Safe Reasoning
Zeming Wei, Qiaosheng Zhang, Xia Hu +1
Large Reasoning Models (LRMs) have achieved tremendous success with their chain-of-thought (CoT) reasoning, yet also face safety issues similar to those of basic language models. I…
cs.LG2025
Reliable Unlearning Harmful Information in LLMs with Metamorphosis Representation Projection
Chengcan Wu, Zeming Wei, Huanran Chen +2
While Large Language Models (LLMs) have demonstrated impressive performance in various domains and tasks, concerns about their safety are becoming increasingly severe. In particula…
cs.LG2025
Towards the Worst-case Robustness of Large Language Models
Huanran Chen, Yinpeng Dong, Zeming Wei +2
Recent studies have revealed the vulnerability of large language models to adversarial attacks, where adversaries craft specific input sequences to induce harmful, violent, private…