Metraipolis › archive › dc_b0d807bed7db
Designing Behavioral Profiles for Language Model Simulation of Out-of-Distribution Human Behavior — arXiv:2611.00661
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.00661
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T10:31:29.933Z
- SHA-256 of the archived text
8adad8086909b5ab6620ee5aada44030b71e0dcf32234c8f512ba3ec631f6254- Stable URL of this page
https://metraipolis.com/documento/dc_b0d807bed7db
How to cite
Designing Behavioral Profiles for Language Model Simulation of Out-of-Distribution Human Behavior — arXiv:2611.00661 — arXiv (en), https://arxiv.org/abs/2611.00661 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b0d807bed7db (Metraipolis archive dc_b0d807bed7db, sha256 8adad8086909b5ab6620ee5aada44030b71e0dcf32234c8f512ba3ec631f6254)
BibTeX
@misc{dcb0d807bed7db,
title = {Designing Behavioral Profiles for Language Model Simulation of Out-of-Distribution Human Behavior — arXiv:2611.00661},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.00661},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b0d807bed7db; sha256 8adad8086909b5ab6620ee5aada44030b71e0dcf32234c8f512ba3ec631f6254},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00661. 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 behavior, but which descriptions of people improve prediction when experimental designs change remains unclear. We develop a framework that draws candidate behavioral features from the literature and constructs profiles from earlier human experiments. A profile-generation LLM assigns feature values from observed actions, messages, and surveys; a separate LLM simulates behavior using these profiles. By comparing simulated and observed outcomes in the learning data, we select profile contents through forward feature selection, adding features while they improve prediction. We then evaluate the selected contents without modification against outcomes from new participants under new designs. Across 616 public-goods games, 144 multi-party bargaining games, and 1,480 generalized 11-20 money-request designs, leading one-feature profiles predict human outcome distributions better than no profile or general-purpose personas. Profiles with more features provide no clear additional benefit, and features' relative predictive value largely persists across learning and validation. Using profiles from one game family to simulate another produces uneven gains and can make predictions less accurate than simulations without profiles. The framework makes the choice of behavioral information a testable part of simulation design, helping researchers assess which descriptions remain useful as experimental conditions change. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI) ; General Economics (econ.GN). Pagina del lavoro: https://arxiv.org/abs/2611.00661 — 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 2026-11-03T10:29:48.470Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).