CoMMET: A Psychologically Grounded Benchmark for Evaluating Theory of Mind in Multimodal LLMs

arXiv:2603.11915 · cs.CL · Submitted 2026-03-12 · Read on arXiv

cs.CL

Submitted: 2026-03-12

Updated: 2026-09-01

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 36× in this paper · explained in 2 episodes
• Theory of Mind — 31× in this paper
• Accuracy — 12× in this paper · explained in 1 episode
• Multimodal Dataset — 4× in this paper · explained in 2 episodes
• Theory of Mind (ToM) — 3× in this paper · explained in 2 episodes
• Interpretability — 2× in this paper · explained in 15 episodes
• Large Language Models (LLMs) — 2× in this paper · explained in 6 episodes
• Benchmarking — 1× in this paper · explained in 4 episodes
• Contextual Understanding — 1× in this paper · explained in 2 episodes
• EMMA — 1× in this paper · explained in 2 episodes
• Multimodal Inputs — 1× in this paper · explained in 2 episodes

Sources

• Large Language Models Fail on Trivial Alterations to Theory-of-Mind Tasks

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering