Paper

{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.11915v1</id>\n    <title>CoMMET: To What Extent Can LLMs Perform Theory of Mind Tasks?</title>\n    <updated>2026-03-12T13:29:42Z</updated>\n    <link href='https://arxiv.org/abs/2603.11915v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.11915v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Theory of Mind (ToM)-the ability to reason about the mental states of oneself and others-is a cornerstone of human social intelligence. As Large Language Models (LLMs) become ubiquitous in real-world applications, validating their capacity for this level of social reasoning is essential for effective and natural interactions. However, existing benchmarks for assessing ToM in LLMs are limited; most rely solely on text inputs and focus narrowly on belief-related tasks. In this paper, we propose a new multimodal benchmark dataset, CoMMET, a Comprehensive Mental states and Moral Evaluation Task inspired by the Theory of Mind Booklet Task. CoMMET expands the scope of evaluation by covering a broader range of mental states and introducing multi-turn testing. To the best of our knowledge, this is the first multimodal dataset to evaluate ToM in a multi-turn conversational setting. Through a comprehensive assessment of LLMs across different families and sizes, we analyze the strengths and limitations of current models and identify directions for future improvement. Our work offers a deeper understanding of the social cognitive capabilities of modern LLMs.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CL'/>\n    <published>2026-03-12T13:29:42Z</published>\n    <arxiv:primary_category term='cs.CL'/>\n    <author>\n      <name>Ruirui Chen</name>\n    </author>\n    <author>\n      <name>Weifeng Jiang</name>\n    </author>\n    <author>\n      <name>Chengwei Qin</name>\n    </author>\n    <author>\n      <name>Cheston Tan</name>\n    </author>\n  </entry>"
}