4 papers
MedCoAct: Confidence-Aware Multi-Agent Collaboration for Complete Clinical Decision
Hongjie Zheng, Zesheng Shi, Ping Yi
Autonomous agents utilizing Large Language Models (LLMs) have demonstrated remarkable capabilities in isolated medical tasks like diagnosis and image analysis, but struggle with in…
Jailbreak-R1: Exploring the Jailbreak Capabilities of LLMs via Reinforcement Learning
Weiyang Guo, Zesheng Shi, Zhuo Li +6
As large language models (LLMs) grow in power and influence, ensuring their safety and preventing harmful output becomes critical. Automated red teaming serves as a tool to detect…
Safety Alignment via Constrained Knowledge Unlearning
Zesheng Shi, Yucheng Zhou, Jing Li
Despite significant progress in safety alignment, large language models (LLMs) remain susceptible to jailbreak attacks. Existing defense mechanisms have not fully deleted harmful k…
Topic-Selective Graph Network for Topic-Focused Summarization
Shi Zesheng, Zhou Yucheng
Due to the success of the pre-trained language model (PLM), existing PLM-based summarization models show their powerful generative capability. However, these models are trained on…