11 papers
Large Language Model Agents Are Not Always Faithful Self-Evolvers
Weixiang Zhao, Yingshuo Wang, Yichen Zhang +5
Self-evolving large language model (LLM) agents continually improve by accumulating and reusing past experience, yet it remains unclear whether they faithfully rely on that experie…
MHSafeEval: Role-Aware Interaction-Level Evaluation of Mental Health Safety in Large Language Models
Suhyun Lee, Palakorn Achananuparp, Neemesh Yadav +2
Large language models (LLMs) are increasingly explored as scalable tools for mental health counseling, yet evaluating their safety remains challenging due to the interactional and…
On Safety Risks in Experience-Driven Self-Evolving Agents
Weixiang Zhao, Yichen Zhang, Yingshuo Wang +8
Experience-driven self-evolution has emerged as a promising paradigm for improving the autonomy of large language model agents, yet its reliance on self-curated experience introduc…
When Less Language is More: Language-Reasoning Disentanglement Makes LLMs Better Multilingual Reasoners
Weixiang Zhao, Jiahe Guo, Yang Deng +9
Multilingual reasoning remains a significant challenge for large language models (LLMs), with performance disproportionately favoring high-resource languages. Drawing inspiration f…
Trade-offs in Large Reasoning Models: An Empirical Analysis of Deliberative and Adaptive Reasoning over Foundational Capabilities
Weixiang Zhao, Xingyu Sui, Jiahe Guo +9
Recent advancements in Large Reasoning Models (LRMs), such as OpenAI's o1/o3 and DeepSeek-R1, have demonstrated remarkable performance in specialized reasoning tasks through human-…
AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender
Weixiang Zhao, Jiahe Guo, Yulin Hu +8
Despite extensive efforts in safety alignment, large language models (LLMs) remain vulnerable to jailbreak attacks. Activation steering offers a training-free defense method but re…