EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Using large language models to categorize strategic situations and decipher motivations behind human behaviors

Yutong Xie iD, Qiaozhu Mei iD, Walter Yuan, Matthew O Jackson iD

Proceedings of the National Academy of Sciences · 02.09.2025 · 122 (35)

DOI: 10.1073/pnas.2512075122 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the National Academy of Sciences, online erschienen am 28.08.2025. Verfasst von Yutong Xie und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Information, University of Michigan, Ann Arbor, MI 48109. Hauptthemen laut MEDLINE: Motivation, Language, Behavior, Models, Psychological. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 19 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

By varying prompts to a large language model, we can elicit the full range of human behaviors in a variety of different scenarios in classic economic games. By analyzing which prompts elicit which behaviors, we can categorize and compare different strategic situations, which can also help provide insight into what different economic scenarios might induce people to think about. We discuss how this provides a step toward a nonstandard method of inferring (deciphering) the motivations behind the human behaviors. We also show how this deciphering process can be used to categorize differences in the behavioral tendencies of different populations.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

MotivationLanguageBehaviorModels, PsychologicalModels, TheoreticalHumansGame TheoryLarge Language Models

Stichwörter der Autor:innen

AIgameshuman behaviormotivationstrategy

Autor:innen und Institutionen

  • School of Information, University of Michigan, Ann Arbor, MI 48109.
  • MobLab, Pasadena, CA 91107.
  • Department of Economics, Stanford University, Stanford, CA 94305.
  • External Faculty, Santa Fe Institute, Santa Fe, NM 87501.

ORCID-Profile: Yutong Xie, Qiaozhu Mei, Matthew O Jackson

Zitieren

APA

Xie, Y., Mei, Q., Yuan, W., & Jackson, M. O. (2025). Using large language models to categorize strategic situations and decipher motivations behind human behaviors. Proceedings of the National Academy of Sciences, 122(35). https://doi.org/10.1073/pnas.2512075122

Vancouver

Xie Y, Mei Q, Yuan W, Jackson MO. Using large language models to categorize strategic situations and decipher motivations behind human behaviors. Proceedings of the National Academy of Sciences. 2025;122(35). doi:10.1073/pnas.2512075122

BibTeX
@article{Xie2025,
  author = {Xie, Yutong and Mei, Qiaozhu and Yuan, Walter and Jackson, Matthew O},
  title = {Using large language models to categorize strategic situations and decipher motivations behind human behaviors},
  journal = {Proceedings of the National Academy of Sciences},
  year = {2025},
  volume = {122},
  number = {35},
  doi = {10.1073/pnas.2512075122}
}
Kostenlos starten →