Metraipolis › archive › dc_4b60d910007d

Exploit or conform? How norm utility prompting changes the way LLMs use community beliefs — arXiv:2611.04048

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.04048
License (as archived)
CC0-1.0
Archived
2026-11-04T12:27:36.721Z
SHA-256 of the archived text
a8ed45dd4370be772a9f3b62e3afdc6ab13691325bf0ff870aa9fcdb89d70ddd
Stable URL of this page
https://metraipolis.com/documento/dc_4b60d910007d

How to cite

Exploit or conform? How norm utility prompting changes the way LLMs use community beliefs — arXiv:2611.04048 — arXiv (en), https://arxiv.org/abs/2611.04048 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4b60d910007d (Metraipolis archive dc_4b60d910007d, sha256 a8ed45dd4370be772a9f3b62e3afdc6ab13691325bf0ff870aa9fcdb89d70ddd)
BibTeX
@misc{dc4b60d910007d,
  title = {Exploit or conform? How norm utility prompting changes the way LLMs use community beliefs — arXiv:2611.04048},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.04048},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4b60d910007d; sha256 a8ed45dd4370be772a9f3b62e3afdc6ab13691325bf0ff870aa9fcdb89d70ddd},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04048. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large Language Models (LLMs) serve both as tools for aiding human decision-making in everyday life and as models of human agents in experimental simulation studies. Alignment on prototypical social decisions -- such as whether to cooperate on a collective action -- therefore has immediate practical consequences for researchers and for society at large. Here we systematically explore the impact of ``norm utility'' -- the non-material components of utility that account for an individual's desire to conform to social norms and to be internally consistent -- on the strategic decision-making of three open-weight LLMs in one-shot, two-player social dilemmas. We find that when a social dilemma is presented together with information about community beliefs -- but without any indication of how those beliefs should matter -- models tend to treat community belief as strategic information, so that in the Snowdrift game cooperation falls as community belief in cooperation increases. When we explicitly prompt the components of norm utility this relationship inverts, and cooperation increases with community belief, in broad agreement with the predictions of a simple norm utility model. We then show that prompting norm utility reduces the volatility of strategic decisions with respect to changes in the underlying social context, and generates more consistent reasoning habits across models. Taken together, our results suggest that prompting norm utility can help generate more human-like and consistent behavior across models and lower volatility within models.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.04048 — 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 2026-11-04T12:26:47.117Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).