EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Large language models accurately identify decision reasons in verbal reports

Kamil Fuławka iD, Ralph Hertwig, Dirk U Wulff

Proceedings of the National Academy of Sciences · 07.07.2026 · 123 (27)

DOI: 10.1073/pnas.2526798123 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the National Academy of Sciences, online erschienen am 30.06.2026. Verfasst von Kamil Fuławka und 2 weiteren Autor:innen. Beteiligte Einrichtung: Center Synergy of Systems, Dresden University of Technology, Dresden 01069, Germany. Hauptthemen laut MEDLINE: Decision Making. Die Arbeit nennt 59 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Understanding the reasons behind human choices under risk is a central goal of decision scientists, but traditional methods relying on behavioral data are limited by strict invariance assumptions. We introduce a scalable analytical framework using large language models (LLMs) to analyze verbal reports and identify articulated reasons for choice between monetary lotteries. A validated LLM accurately identified predefined decision reasons in participants’ free-text reports, aligning with their actual choices in 95% of trials. Our analysis reveals that the reasons behind people’s decisions vary systematically and are driven more by the structure of the choice problem than by individual differences. Crucially, reasons identified from verbal reports yield more parsimonious and informative representations of decision processes compared to those inferred from choices alone; furthermore, problem-specific reason profiles achieve out-of-sample prediction accuracy that is competitive with established computational models. This work demonstrates that verbal reports are a rich data source and our analytical framework can unlock their potential, delivering results that challenge the field’s foundational invariance assumptions and pave the way for more context-sensitive and interpretable models of human decision making.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Decision MakingHumansLarge Language ModelsChoice Behavior

Stichwörter der Autor:innen

decision makinglarge language modelsprospect theoryrisky choiceverbal reports

Autor:innen und Institutionen

  • Center Synergy of Systems, Dresden University of Technology, Dresden 01069, Germany.
  • Center for Adaptive Rationality, Max Planck Institute for Human Development, Berlin 14195, Germany.
  • Faculty of Psychology, University of Basel, Basel 4055, Switzerland.

ORCID-Profile: Kamil Fuławka

Zitieren

APA

Fuławka, K., Hertwig, R., & Wulff, D. U. (2026). Large language models accurately identify decision reasons in verbal reports. Proceedings of the National Academy of Sciences, 123(27). https://doi.org/10.1073/pnas.2526798123

Vancouver

Fuławka K, Hertwig R, Wulff DU. Large language models accurately identify decision reasons in verbal reports. Proceedings of the National Academy of Sciences. 2026;123(27). doi:10.1073/pnas.2526798123

BibTeX
@article{Fuawka2026,
  author = {Fuławka, Kamil and Hertwig, Ralph and Wulff, Dirk U},
  title = {Large language models accurately identify decision reasons in verbal reports},
  journal = {Proceedings of the National Academy of Sciences},
  year = {2026},
  volume = {123},
  number = {27},
  doi = {10.1073/pnas.2526798123}
}
Kostenlos starten →