Re-evaluating Theory of Mind evaluation in large language models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hu, Jennifer, Sosa, Felix, Ullman, Tomer
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909517172703232
author Hu, Jennifer
Sosa, Felix
Ullman, Tomer
author_facet Hu, Jennifer
Sosa, Felix
Ullman, Tomer
contents The question of whether large language models (LLMs) possess Theory of Mind (ToM) -- often defined as the ability to reason about others' mental states -- has sparked significant scientific and public interest. However, the evidence as to whether LLMs possess ToM is mixed, and the recent growth in evaluations has not resulted in a convergence. Here, we take inspiration from cognitive science to re-evaluate the state of ToM evaluation in LLMs. We argue that a major reason for the disagreement on whether LLMs have ToM is a lack of clarity on whether models should be expected to match human behaviors, or the computations underlying those behaviors. We also highlight ways in which current evaluations may be deviating from "pure" measurements of ToM abilities, which also contributes to the confusion. We conclude by discussing several directions for future research, including the relationship between ToM and pragmatic communication, which could advance our understanding of artificial systems as well as human cognition.
format Preprint
id arxiv_https___arxiv_org_abs_2502_21098
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Re-evaluating Theory of Mind evaluation in large language models
Hu, Jennifer
Sosa, Felix
Ullman, Tomer
Artificial Intelligence
Computation and Language
The question of whether large language models (LLMs) possess Theory of Mind (ToM) -- often defined as the ability to reason about others' mental states -- has sparked significant scientific and public interest. However, the evidence as to whether LLMs possess ToM is mixed, and the recent growth in evaluations has not resulted in a convergence. Here, we take inspiration from cognitive science to re-evaluate the state of ToM evaluation in LLMs. We argue that a major reason for the disagreement on whether LLMs have ToM is a lack of clarity on whether models should be expected to match human behaviors, or the computations underlying those behaviors. We also highlight ways in which current evaluations may be deviating from "pure" measurements of ToM abilities, which also contributes to the confusion. We conclude by discussing several directions for future research, including the relationship between ToM and pragmatic communication, which could advance our understanding of artificial systems as well as human cognition.
title Re-evaluating Theory of Mind evaluation in large language models
topic Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2502.21098