作者位次 #2/4ACL 2026Findings· Findings of ACL
Jailbreaking Large Language Models with Morality Attacks
Ying Su · Zheng Mingen · Weili Diao · Haoran Li
摘要
Pluralism alignment with AI has the sophisticated and necessary goal of creating AI that can coexist with and serve morally multifaceted humanity. Research towards pluralism alignment has many efforts in enhancing the learning of large language models (LLMs) to accomplish pluralism. Although this...