EUVIMEDEUVIMED entdecken
Open Access

Relevant answers to polar questions

Robert D Hawkins iD, Polina Tsvilodub, Claire Augusta Bergey iD, Noah D Goodman, Michael Franke

Philosophical Transactions of the Royal Society B: Biological Sciences · 2025

DOI: 10.1098/rstb.2023.0505 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Philosophical Transactions of the Royal Society B: Biological Sciences, 2025. Verfasst von Robert D Hawkins und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Linguistics, Stanford University, Stanford, CA 94305, USA. Hauptthemen laut MEDLINE: Theory of Mind, Communication, Language, Cognition. Die Arbeit nennt 65 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: Deutsche Forschungsgemeinschaft, Division of Behavioral and Cognitive Sciences, NSF.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

People often provide answers that go beyond what a question literally asks, but it has been difficult to pin down what makes some answers more relevant than others. Here, we introduce Pragmatic Reasoning In Overinformative Responses to Polar Questions (PRIOR-PQ), a probabilistic cognitive model formalizing how people use theory of mind (ToM) to produce and interpret relevantly overinformative answers to yes–no questions. Specifically, PRIOR-PQ grounds the pragmatics of question answering in inferences about the underlying goal that motivated the questioner to ask the given question as opposed to a different question. We evaluate our probabilistic model against human answering behaviour elicited in three case studies of increasing complexity, demonstrating its ability to predict nuanced patterns of relevance better than existing models, including state-of-the-art large language models. We also show how the goal-sensitive reasoning instantiated in our probabilistic model motivates a novel chain-of-thought prompting method allowing language models to approach more human-like performance. This work illuminates the mechanistic role of ToM in the pragmatics of question–answer exchanges, bridging formal semantics, cognitive science and artificial intelligence. Our findings have implications for developing more socially grounded dialogue systems and highlight the importance of integrating explanatory cognitive models with machine learning approaches. This article is part of the theme issue ‘At the heart of human communication: new views on the complex relationship between pragmatics and Theory of Mind’.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Theory of MindCommunicationLanguageCognitionThinkingHumans

Stichwörter der Autor:innen

computational modelinglarge language modelspragmatic reasoningprobabilistic pragmaticsquestion–answer dialoguetheory of mind

Autor:innen und Institutionen

  • Department of Linguistics, Stanford University, Stanford, CA 94305, USA.
  • Eberhard Karls Universitat Tubingen, Tubingen, Baden-Württemberg 72074, Germany.
  • Department of Psychology and Computer Science, Stanford University, Stanford, CA 94305, USA.

ORCID-Profile: Robert D Hawkins, Claire Augusta Bergey

Förderung

  • Deutsche Forschungsgemeinschaft
  • Division of Behavioral and Cognitive Sciences
  • NSF

Zitieren

APA

Hawkins, R. D., Tsvilodub, P., Bergey, C. A., Goodman, N. D., & Franke, M. (2025). Relevant answers to polar questions. Philosophical Transactions of the Royal Society B: Biological Sciences. https://doi.org/10.1098/rstb.2023.0505

Vancouver

Hawkins RD, Tsvilodub P, Bergey CA, Goodman ND, Franke M. Relevant answers to polar questions. Philosophical Transactions of the Royal Society B: Biological Sciences. 2025. doi:10.1098/rstb.2023.0505

BibTeX
@article{Hawkins2025,
  author = {Hawkins, Robert D and Tsvilodub, Polina and Bergey, Claire Augusta and Goodman, Noah D and Franke, Michael},
  title = {Relevant answers to polar questions},
  journal = {Philosophical Transactions of the Royal Society B: Biological Sciences},
  year = {2025},
  doi = {10.1098/rstb.2023.0505}
}
Kostenlos starten →