MENTOR: A Metacognition-Driven Self-Evolution Framework for Uncovering and Mitigating Implicit Domain Risks in LLMs 文章
ArXiv CS.CL2026-06-04NEWSen作者: Liang Shan, Kaicheng Shen, Wen Wu, Zhenyu Ying, Chaochao Lu, Yan Teng, Jingqi Huang, Qingshan Liu, Guangze Ye, Guoqing Wang, Jie Zhou, Liang He