MuSeToM: Multi-Sensory Evaluation of Belief Revision with Textual Cues Across Six Senses

Theory of Mind (ToM), the ability to infer mental states in others, is pivotal for human social cognition. Existing evaluations of ToM in large language models (LLMs) mainly focus on static belief attribution and false-belief reasoning, leaving a critical aspect of social reasoning underexplored: can LLMs decide whether perceptual evidence is sufficient to justify another person's belief revision? To address this gap, we present MuSeToM, a human-validated, text-based benchmark for evaluating epistemic belief revision in ToM reasoning. MuSeToM contains 2,415 instances adapted from BigToM and OpenToM, with textual cues spanning six sensory categories, and tests whether models can determine when a protagonist should revise a belief and infer the resulting updated belief state. Using MuSeToM, we systematically evaluate state-of-the-art LLMs under direct and chain-of-thought prompting, revealing a pronounced dissonance: while models often detect that a belief may change, they struggle to identify the updated belief and frequently over-update on perceptually salient but epistemically insufficient cues.

Authors

Publication Details

Journal
arXiv (Cornell University)
Published
2026-11-12
DOI
https://doi.org/10.48550/arxiv.2611.16662
Primary Topic
Child and Animal Learning Development
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

MuSeToM: Multi-Sensory Evaluation of Belief Revision with Textual Cues Across Six Senses

Chunkit Chan, Xiaoman Pan, Tianshi Zheng, Ginny Y. Wong et al.
arXiv (Cornell University)
Child and Animal Learning Development
preprint

MuSeToM: Multi-Sensory Evaluation of Belief Revision with Textual Cues Across Six Senses

Chunkit Chan, Xiaoman Pan, Tianshi Zheng, Ginny Y. Wong, Simon Chong Wee See, Qing Zong, Yauwai Yim, Sze Heng Douglas Kwok, Kawai Chung, Kai Chung Wong, Yifan Gao, Yangqiu Song, Pak Hin Lau, Haochen Shi, Yuxuan Liu, Calvin Yang
preprint en

Abstract

Theory of Mind (ToM), the ability to infer mental states in others, is pivotal for human social cognition. Existing evaluations of ToM in large language models (LLMs) mainly focus on static belief attribution and false-belief reasoning, leaving a critical aspect of social reasoning underexplored: can LLMs decide whether perceptual evidence is sufficient to justify another person's belief revision? To address this gap, we present MuSeToM, a human-validated, text-based benchmark for evaluating epistemic belief revision in ToM reasoning. MuSeToM contains 2,415 instances adapted from BigToM and OpenToM, with textual cues spanning six sensory categories, and tests whether models can determine when a protagonist should revise a belief and infer the resulting updated belief state. Using MuSeToM, we systematically evaluate state-of-the-art LLMs under direct and chain-of-thought prompting, revealing a pronounced dissonance: while models often detect that a belief may change, they struggle to identify the updated belief and frequently over-update on perceptually salient but epistemically insufficient cues.

arXiv (Cornell University)
Child and Animal Learning Development
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon