Metraipolis › archive › dc_8c19fb7870ea

Toward a social psychology of AI: language-model agents reproduce human-like minimal-group bias — arXiv:2609.00009

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.00009
License (as archived): CC0-1.0
Archived: 2026-10-17T06:42:25.135Z
SHA-256 of the archived text: c8d9dbab4dd82586a4facd2eec7be5d2e2ea1f9402bd614113da6c6fa32ad4be
Stable URL of this page: https://metraipolis.com/documento/dc_8c19fb7870ea

How to cite

Toward a social psychology of AI: language-model agents reproduce human-like minimal-group bias — arXiv:2609.00009 — arXiv (en), https://arxiv.org/abs/2609.00009 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8c19fb7870ea (Metraipolis archive dc_8c19fb7870ea, sha256 c8d9dbab4dd82586a4facd2eec7be5d2e2ea1f9402bd614113da6c6fa32ad4be)

BibTeX

@misc{dc8c19fb7870ea,
  title = {Toward a social psychology of AI: language-model agents reproduce human-like minimal-group bias — arXiv:2609.00009},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.00009},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8c19fb7870ea; sha256 c8d9dbab4dd82586a4facd2eec7be5d2e2ea1f9402bd614113da6c6fa32ad4be},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.00009. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Language-model agents now interact in groups, but evaluations that probe memorised stereotype content or use models to simulate people leave this social behaviour unmeasured. We adapt the minimal-group paradigm---social psychology's classic test of intergroup bias---into a controlled probe: an agent distributes points among anonymous peers bearing only an arbitrary group label. Across four reasoning models, mere categorisation into meaningless groups elicited in-group favouritism that vanished under a group-blind control and was concentrated in the numerical minority: minority deciders over-allocated to their own group relative to their numbers, majority deciders allocated close to proportionally, and the asymmetry closed at equal group sizes. Disabling reasoning in one model did not remove the disposition---if anything it grew---but nearly erased the minority-majority asymmetry, implicating deliberation in where bias concentrates rather than whether it appears. These open-weight reasoning models reproduce the behavioural signature of human intergroup discrimination, independent of stereotype content, and social psychology's theories and methods offer a paradigm for measuring and governing AI's social behaviour.

Tema degli esploratori: governance digitale e beni comuni (retro-catalogo arXiv: annunci del 2026-09-02 in cs.CY).
Categorie arXiv: Physics and Society (physics.soc-ph) ; Computers and Society (cs.CY).
Pagina del lavoro: https://arxiv.org/abs/2609.00009 — 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 2026-10-17T06:36:58.685Z dalla pagina https://arxiv.org/catchup/cs.CY/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).