CogToM: A Comprehensive Theory of Mind Benchmark inspired by Human Cognition for Large Language Models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911391801147392 |
|---|---|
| author | Tong, Haibo Yue, Zeyang Zhao, Feifei Lin, Erliang Jia, Lu Chen, Ruolin Sun, Yinqian Zhang, Qian Zeng, Yi |
| author_facet | Tong, Haibo Yue, Zeyang Zhao, Feifei Lin, Erliang Jia, Lu Chen, Ruolin Sun, Yinqian Zhang, Qian Zeng, Yi |
| contents | Whether Large Language Models (LLMs) truly possess human-like Theory of Mind (ToM) capabilities has garnered increasing attention. However, existing benchmarks remain largely restricted to narrow paradigms like false belief tasks, failing to capture the full spectrum of human cognitive mechanisms. We introduce CogToM, a comprehensive, theoretically grounded benchmark comprising over 8000 bilingual instances across 46 paradigms, validated by 49 human annotator.A systematic evaluation of 22 representative models, including frontier models like GPT-5.1 and Qwen3-Max, reveals significant performance heterogeneities and highlights persistent bottlenecks in specific dimensions. Further analysis based on human cognitive patterns suggests potential divergences between LLM and human cognitive structures. CogToM offers a robust instrument and perspective for investigating the evolving cognitive boundaries of LLMs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_15628 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | CogToM: A Comprehensive Theory of Mind Benchmark inspired by Human Cognition for Large Language Models Tong, Haibo Yue, Zeyang Zhao, Feifei Lin, Erliang Jia, Lu Chen, Ruolin Sun, Yinqian Zhang, Qian Zeng, Yi Artificial Intelligence Whether Large Language Models (LLMs) truly possess human-like Theory of Mind (ToM) capabilities has garnered increasing attention. However, existing benchmarks remain largely restricted to narrow paradigms like false belief tasks, failing to capture the full spectrum of human cognitive mechanisms. We introduce CogToM, a comprehensive, theoretically grounded benchmark comprising over 8000 bilingual instances across 46 paradigms, validated by 49 human annotator.A systematic evaluation of 22 representative models, including frontier models like GPT-5.1 and Qwen3-Max, reveals significant performance heterogeneities and highlights persistent bottlenecks in specific dimensions. Further analysis based on human cognitive patterns suggests potential divergences between LLM and human cognitive structures. CogToM offers a robust instrument and perspective for investigating the evolving cognitive boundaries of LLMs. |
| title | CogToM: A Comprehensive Theory of Mind Benchmark inspired by Human Cognition for Large Language Models |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2601.15628 |