{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/enigmatom-improve-llms-theory-of-mind","title":"EnigmaToM: Improve LLMs' Theory-of-Mind Reasoning Capabilities with Neural Knowledge Base of Entity States","arxiv_id":"2503.03340","date":"2025-03-05","proceeding":null,"authors":["Hainiu Xu","Siya Qi","Jiazheng Li","Yuxiang Zhou","Jinhua Du","Caroline Catmur","Yulan He"],"abstract":"Theory-of-Mind (ToM), the ability to infer others' perceptions and mental states, is fundamental to human interaction but remains a challenging task for Large Language Models (LLMs). While existing ToM reasoning methods show promise with reasoning via perceptual perspective-taking, they often rely excessively on LLMs, reducing their efficiency and limiting their applicability to high-order ToM reasoning, which requires multi-hop reasoning about characters' beliefs. 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 representations of entity states, which construct spatial scene graphs -- leveraging spatial information as an inductive bias -- for belief tracking of various ToM orders and enhancing events with fine-grained entity state details. Experimental results on multiple benchmarks, including ToMi, HiToM, and FANToM, show that EnigmaToM significantly improves ToM reasoning across LLMs of varying sizes, particularly excelling in high-order reasoning scenarios.","url_abs":"https://arxiv.org/abs/2503.03340v1","url_pdf":"https://arxiv.org/pdf/2503.03340v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"enigmatom-improve-llms-theory-of-mind","repo_url":"https://github.com/seacowx/EnigmaToM","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"inductive-bias","task_name":"Inductive Bias"}],"methods":[{"method_slug":"base","method_name":"BASE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}