AI RESEARCH
Jailbreaking Large Language Models with Morality Attacks
arXiv CS.CL
•
ArXi:2604.17053v1 Announce Type: new 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 is essential, the robustness of LLMs to produce moral content over pluralistic values is still under exploration.