Metraipolis › archive › dc_a7b669c59540

Moral Combat: Exploiting Moral Foundations Theory to Jailbreak LLMs — arXiv:2610.19587

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.19587
License (as archived): CC0-1.0
Archived: 2026-10-15T20:24:04.387Z
SHA-256 of the archived text: 0fc025265e93574eabace31f71ccd49c1c2fb82f48d7218fe40f617779266b21
Stable URL of this page: https://metraipolis.com/documento/dc_a7b669c59540

How to cite

Moral Combat: Exploiting Moral Foundations Theory to Jailbreak LLMs — arXiv:2610.19587 — arXiv (en), https://arxiv.org/abs/2610.19587 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a7b669c59540 (Metraipolis archive dc_a7b669c59540, sha256 0fc025265e93574eabace31f71ccd49c1c2fb82f48d7218fe40f617779266b21)

BibTeX

@misc{dca7b669c59540,
  title = {Moral Combat: Exploiting Moral Foundations Theory to Jailbreak LLMs — arXiv:2610.19587},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.19587},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a7b669c59540; sha256 0fc025265e93574eabace31f71ccd49c1c2fb82f48d7218fe40f617779266b21},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.19587. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Social psychology has long described how people can be persuaded to interpret a harmful act as moral. Recent research suggests that Large Language Models (LLMs) echo aspects of human psychology, from cognitive biases to social conformity. This raises a question with direct safety implications: can LLMs be moralized to bypass safety guardrails? We answer this question with a multi-agent framework grounded in Moral Foundations Theory (MFT). Given a harmful request that is initially refused, our agents diagnose which moral foundation (MF) the prompt is violating, identify a justifiable foundation under which the same request appears virtuous, rewrite the prompt accordingly, and reinforce it with generated precedents of comparable moral reframing. We evaluate our framework on harmful prompts from three well-known jailbreak datasets across five open-source and proprietary models. Our analysis reveals that models are highly susceptible to moralization, exhibiting high single-trial jailbreak rates with success increasing further under repeated attempts. We also find that safety benchmarks are imbalanced in the MFs they violate, concentrating on foundations toward which models already exhibit biases.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL) ; Computers and Society (cs.CY).
Pagina del lavoro: https://arxiv.org/abs/2610.19587 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-15T19:36:18.202Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).