Knowing-but-Doing: Diagnosing and Defending Role-Play-Driven LLMs Jailbreaks via Moral Disengagement.
Haiming Qin, Jianxun Lian, Qimin Zhong, Mingyang Zhou, Hao Liao, Naipeng Chao
Browse the full ACL paper archive.
Haiming Qin, Jianxun Lian, Qimin Zhong, Mingyang Zhou, Hao Liao, Naipeng Chao
Browse the full ACL paper archive.