{"ID":2898219,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.04189","arxiv_id":"2507.04189","title":"SymbolicThought: Integrating Language Models and Symbolic Reasoning for Consistent and Interpretable Human Relationship Understanding","abstract":"Understanding character relationships is essential for interpreting complex narratives and conducting socially grounded AI research. However, manual annotation is time-consuming and low in coverage, while large language models (LLMs) often produce hallucinated or logically inconsistent outputs. We present SymbolicThought, a human-in-the-loop framework that combines LLM-based extraction with symbolic reasoning. The system constructs editable character relationship graphs, refines them using seven types of logical constraints, and enables real-time validation and conflict resolution through an interactive interface. To support logical supervision and explainable social analysis, we release a dataset of 160 interpersonal relationships with corresponding logical structures. Experiments show that SymbolicThought improves annotation accuracy and consistency while significantly reducing time cost, offering a practical tool for narrative understanding, explainable AI, and LLM evaluation.","short_abstract":"Understanding character relationships is essential for interpreting complex narratives and conducting socially grounded AI research. However, manual annotation is time-consuming and low in coverage, while large language models (LLMs) often produce hallucinated or logically inconsistent outputs. We present SymbolicThoug...","url_abs":"https://arxiv.org/abs/2507.04189","url_pdf":"https://arxiv.org/pdf/2507.04189v2","authors":"[\"Runcong Zhao\",\"Qinglin Zhu\",\"Hainiu Xu\",\"Bin Liang\",\"Lin Gui\",\"Yulan He\"]","published":"2025-07-05T23:46:35Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.AI\",\"cs.HC\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}