@inproceedings{xu-etal-2025-enigmatom,
    title = "{E}nigma{T}o{M}: Improve {LLM}s' Theory-of-Mind Reasoning Capabilities with Neural Knowledge Base of Entity States",
    author = "Xu, Hainiu  and
      Qi, Siya  and
      Li, Jiazheng  and
      Zhou, Yuxiang  and
      Du, Jinhua  and
      Catmur, Caroline  and
      He, Yulan",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/mtsummit-25-ingestion/2025.findings-acl.699/",
    doi = "10.18653/v1/2025.findings-acl.699",
    pages = "13598--13622",
    ISBN = "979-8-89176-256-5",
    abstract = "Theory-of-Mind (ToM), the ability to infer others' perceptions and mental states, is fundamental to human interaction but remains challenging for Large Language Models (LLMs). While existing ToM reasoning methods show promise with reasoning via perceptual perspective-taking, they often rely excessively on off-the-shelf LLMs, reducing their efficiency and limiting their applicability to high-order ToM reasoning. To address these issues, we present EnigmaToM, a novel neuro-symbolic framework that enhances ToM reasoning by integrating a Neural Knowledge Base of entity states (Enigma) for (1) a psychology-inspired iterative masking mechanism that facilitates accurate perspective-taking and (2) knowledge injection that elicits key entity information. Enigma generates structured knowledge of entity states to build spatial scene graphs for belief tracking across various ToM orders and enrich events with fine-grained entity state details. Experimental results on ToMi, HiToM, and FANToM benchmarks show that EnigmaToM significantly improves ToM reasoning across LLMs of varying sizes, particularly excelling in high-order reasoning scenarios."
}