Self-Persuasion: A Novel Cognitive Approach to Effective LLM Jailbreaking.
Zhenhua Wang, Wei Xie, Shuoyoucheng Ma, Xiaobing Sun, Baosheng Wang, Zhihua Wen, Enze Wang, Kai Chen
Browse the full CogSci paper archive.
Zhenhua Wang, Wei Xie, Shuoyoucheng Ma, Xiaobing Sun, Baosheng Wang, Zhihua Wen, Enze Wang, Kai Chen
Browse the full CogSci paper archive.