Metraipolis › archive › dc_ecc19479af3f

Conditioning LLMs on Social Value Orientation improves behavioural alignment in a sequential social dilemma — arXiv:2610.01667

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.01667
License (as archived)
CC0-1.0
Archived
2026-10-06T14:08:17.132Z
SHA-256 of the archived text
370c22c649e392233d6002685e2950463d7397a24b7b9b222c606c229ce16c9d
Stable URL of this page
https://metraipolis.com/documento/dc_ecc19479af3f

How to cite

Conditioning LLMs on Social Value Orientation improves behavioural alignment in a sequential social dilemma — arXiv:2610.01667 — arXiv (en), https://arxiv.org/abs/2610.01667 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ecc19479af3f (Metraipolis archive dc_ecc19479af3f, sha256 370c22c649e392233d6002685e2950463d7397a24b7b9b222c606c229ce16c9d)
BibTeX
@misc{dcecc19479af3f,
  title = {Conditioning LLMs on Social Value Orientation improves behavioural alignment in a sequential social dilemma — arXiv:2610.01667},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.01667},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ecc19479af3f; sha256 370c22c649e392233d6002685e2950463d7397a24b7b9b222c606c229ce16c9d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.01667. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language Models (LLMs) are increasingly used to simulate human decision-making, yet their outputs often under-represent human behavioural heterogeneity. We investigate whether conditioning LLMs on Social Value Orientation (SVO, a measure of how individuals value their own outcomes relative to others') can better reproduce human behaviour in a sequential social dilemma. Using experimental data from two variants of the Centipede Game (CG) as reference, we compare the default behaviour of eight LLMs with behaviour generated after conditioning them on SVO profiles drawn from the human sample. We find that the default strategies vary substantially across models, but are generally distant from the reference distributions. However, conditioning them on SVO profiles systematically steers their strategic behaviour, improving alignment with the human reference by up to 70% with respect to the default. Across models, higher induced SVO values decrease the probability of stopping the game, reproducing the relationship between prosociality and cooperation observed in human behaviour. Together with the sensitivity of LLMs' elicited SVO to prompt and order effects, these results suggest that the usefulness of SVO for behavioural simulation does not depend on LLMs possessing stable social preferences, but rather on their ability to map social preferences onto corresponding strategic choices.

Tema degli esploratori: economia dei servizi IA (retro-catalogo arXiv: annunci del 2026-10-02 in cs.GT).
Categorie arXiv: Computer Science and Game Theory (cs.GT).
Pagina del lavoro: https://arxiv.org/abs/2610.01667 — 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 2026-10-06T12:27:12.836Z dalla pagina https://arxiv.org/catchup/cs.GT/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).