Cognitive Models for Machine Theory of Mind
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.
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)
Stichwörter der Autor:innen
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}
}
EUVIMED