Metraipolis › archive › dc_57606bcd98bd
The Social World Model Evaluation Gap — arXiv:2610.33014
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.33014
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-27T07:59:23.647Z
- SHA-256 of the archived text
63dda5e17d26448cd25ee6dbd45959b16486b8e588c122dadab60983f11299ef- Stable URL of this page
https://metraipolis.com/documento/dc_57606bcd98bd
How to cite
The Social World Model Evaluation Gap — arXiv:2610.33014 — arXiv (en), https://arxiv.org/abs/2610.33014 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_57606bcd98bd (Metraipolis archive dc_57606bcd98bd, sha256 63dda5e17d26448cd25ee6dbd45959b16486b8e588c122dadab60983f11299ef)
BibTeX
@misc{dc57606bcd98bd,
title = {The Social World Model Evaluation Gap — arXiv:2610.33014},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.33014},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_57606bcd98bd; sha256 63dda5e17d26448cd25ee6dbd45959b16486b8e588c122dadab60983f11299ef},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.33014. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
A negotiation assistant can reach a good deal without accurately predicting the other person's response. We ask whether evaluations of social world models test that prediction directly. We audit 113 works published from 1999 to 2026. 9 primary evaluations measure a real person's response to an action selected by the system or experimenter. Only 2 also compare an explicit response forecast with that response. Their predictors use information available when the action is chosen, and the evaluated responses were excluded from fitting; both randomize the intervention. A separate full-text check of 25 language-model works finds no experiment meeting these conditions. The other evaluations test current-state inference, task success, or prediction from recorded actions. We propose a 1-step negotiation experiment that separates these questions. The findings describe the audited sample, not the prevalence of this evaluation gap across the field. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.33014 — 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 2026-10-27T07:55:30.785Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).