Jailbreaking Large Language Models with Morality Attacks

Abstract

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.Inspired by the astonishing persuasion abilities via jailbreak prompts, we propose to lev

Categories

Framework mappings

Suggested from the entry's categories.

@misc{su2026jailbreaking,
  title = {{Jailbreaking Large Language Models with Morality Attacks}},
  author = {Ying Su and Mingen Zheng and Weili Diao and Haoran Li},
  year = {2026},
  month = apr,
  eprint = {2604.17053},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2604.17053}
}