Metraipolis › archive › dc_54df45a84dcf

Incoherent by Design? On the Moral Self-Consistency of LLMs — arXiv:2608.15354

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.15354
License (as archived)
CC0-1.0
Archived
2026-10-18T17:13:53.543Z
SHA-256 of the archived text
a411273901760c7d1d0b6cda0c3da5d7526aa855ef02149152d53c138e5a908b
Stable URL of this page
https://metraipolis.com/documento/dc_54df45a84dcf

How to cite

Incoherent by Design? On the Moral Self-Consistency of LLMs — arXiv:2608.15354 — arXiv (en), https://arxiv.org/abs/2608.15354 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_54df45a84dcf (Metraipolis archive dc_54df45a84dcf, sha256 a411273901760c7d1d0b6cda0c3da5d7526aa855ef02149152d53c138e5a908b)
BibTeX
@misc{dc54df45a84dcf,
  title = {Incoherent by Design? On the Moral Self-Consistency of LLMs — arXiv:2608.15354},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.15354},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_54df45a84dcf; sha256 a411273901760c7d1d0b6cda0c3da5d7526aa855ef02149152d53c138e5a908b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.15354. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

LLMs are increasingly used in morally sensitive contexts, yet it is unclear whether they apply ethical principles consistently across situations. A model that can state a moral principle may still violate it when the same scenario is rephrased or reframed. This inconsistency is a problem for any system whose outputs are used to inform moral decisions. If generative systems exhibit internal inconsistency, then the epistemic integrity of AI-mediated systems becomes uncertain. To study this concern, we investigate the stability of moral reasoning in LLMs within a controlled prompting framework across three major philosophical schools of thought: deontology, utilitarianism, and virtue ethics. We construct sets of morally equivalent scenarios in which the underlying situation is held constant while the framing varies to reflect different ethical stances and stylistic perturbations. We then evaluate responses from multiple models, including GPT, Mistral, and Llama. To assess consistency, we convert model outputs into structured logical statements and identify contradictions across responses generated within the same school of thought. Our results reveal substantial inconsistency with contradiction rates reaching up to 78% across scenarios. These findings point to a broader phenomenon of epistemic instability in generative AI wherein models fail to reliably maintain coherence with respect to their own prior outputs. This kind of instability carries real consequences. As generative systems influence how people form beliefs, judge actions, and absorb values, their inconsistencies can shape human reasoning and decision-making as well. Moreover, if a system cannot consistently represent its own normative commitments, then value alignment becomes a moving target rather than a well-defined objective. Thus, we argue that demonstrating internal incoherence is a necessary precursor to AI alignment.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.15354 — 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 2026-10-18T16:29:13.792Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).