SymbolicThought：集成语言模型与符号推理以实现一致且可解释的人物关系理解
SymbolicThought: Integrating Language Models and Symbolic Reasoning for Consistent and Interpretable Human Relationship Understanding
AI总结：
提出人在回路框架SymbolicThought，结合LLM提取与符号推理构建可编辑角色关系图，通过七种逻辑约束和交互界面优化验证，并发布160条关系数据集，显著提升标注准确性与一致性并降低时间成本。
摘要：
理解角色关系对于解释复杂叙事和开展具有社会基础的AI研究至关重要。然而，人工标注耗时且覆盖率低，而大型语言模型（LLMs）常产生幻觉或逻辑不一致的输出。我们提出了SymbolicThought，这是一个人在回路框架，结合了基于LLM的提取与符号推理。该系统构建可编辑的角色关系图，使用七种逻辑约束对其进行细化，并通过交互界面实现实时验证和冲突解决。为支持逻辑监督和可解释的社会分析，我们发布了一个包含160种人际关系及其对应逻辑结构的数据集。实验表明，SymbolicThought提高了标注准确性和一致性，同时显著降低了时间成本，为叙事理解、可解释AI和LLM评估提供了实用工具。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
