EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Cognitive Models for Machine Theory of Mind

Christian Lebiere iD, Peter Pirolli iD, Matthew Johnson iD, Michael Martin iD, Donald Morrison iD

Topics in Cognitive Science · 2025

DOI: 10.1111/tops.12773 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Topics in Cognitive Science, 2025. Verfasst von Christian Lebiere und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Psychology, Carnegie Mellon University. Hauptthemen laut MEDLINE: Theory of Mind, Artificial Intelligence, Models, Psychological, Cognition. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 59 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: DARPA, Defense Advanced Research Projects Agency.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Some of the required characteristics for a true machine theory of mind (MToM) include the ability to (1) reproduce the full diversity of human thought and behavior, (2) develop a personalized model of an individual with very limited data, and (3) provide an explanation for behavioral predictions grounded in the cognitive processes of the individual. We propose that a certain class of cognitive models provide an approach that is well suited to meeting those requirements. Being grounded in a mechanistic framework like a cognitive architecture such as ACT‐R naturally fulfills the third requirement by mapping behavior to cognitive mechanisms. Exploiting a modeling paradigm such as instance‐based learning accounts for the first requirement by reflecting variations in individual experience into a diversity of behavior. Mechanisms such as knowledge tracing and model tracing allow a specific run of the cognitive model to be aligned with a given individual behavior trace, fulfilling the second requirement. We illustrate these principles with a cognitive model of decision‐making in a search and rescue task in the Minecraft simulation environment. We demonstrate that cognitive models personalized to individual human players can provide the MToM capability to optimize artificial intelligence agents by diagnosing the underlying causes of observed human behavior, projecting the future effects of potential interventions, and managing the adaptive process of shaping human behavior. Examples of the inputs provided by such analytic cognitive agents include predictions of cognitive load, probability of error, estimates of player self‐efficacy, and trust calibration. Finally, we discuss implications for future research and applications to collective human–machine intelligence.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Theory of MindArtificial IntelligenceModels, PsychologicalCognitionHumansDecision MakingMachine Learning

Stichwörter der Autor:innen

ACT‐RCognitive modelsHuman–machine teamingInstance‐based learningIntelligent agentsModel tracingPersonalizationTheory of mind

Autor:innen und Institutionen

  • Department of Psychology, Carnegie Mellon University.
  • Institute for Human & Machine Cognition, Pensacola.

ORCID-Profile: Christian Lebiere, Peter Pirolli, Matthew Johnson, Michael Martin, Donald Morrison

Förderung

  • DARPA
  • Defense Advanced Research Projects Agency

Zitieren

APA

Lebiere, C., Pirolli, P., Johnson, M., Martin, M., & Morrison, D. (2025). Cognitive Models for Machine Theory of Mind. Topics in Cognitive Science. https://doi.org/10.1111/tops.12773

Vancouver

Lebiere C, Pirolli P, Johnson M, Martin M, Morrison D. Cognitive Models for Machine Theory of Mind. Topics in Cognitive Science. 2025. doi:10.1111/tops.12773

BibTeX
@article{Lebiere2025,
  author = {Lebiere, Christian and Pirolli, Peter and Johnson, Matthew and Martin, Michael and Morrison, Donald},
  title = {Cognitive Models for Machine Theory of Mind},
  journal = {Topics in Cognitive Science},
  year = {2025},
  doi = {10.1111/tops.12773}
}
Kostenlos starten →