用符号推理提升大模型对人物关系的理解一致性与可解释性
SymbolicThought: Integrating Language Models and Symbolic Reasoning for Consistent and Interpretable Human Relationship Understanding
- 结合大模型提取与符号逻辑约束构建可编辑关系图
- 在160组人际关系数据上实现更高准确率与更低标注耗时
- 适合需要可解释性的人文社科研究与大模型评估
理解角色关系对于解析复杂叙事和开展社会基础型人工智能研究至关重要。然而，人工标注耗时且覆盖有限，而大型语言模型常产生幻觉或逻辑不一致的输出。我们提出SymbolicThought，一种人机协同框架，融合基于大模型的关系抽取与符号推理。系统构建可编辑的角色关系图，利用七类逻辑约束进行优化，并通过交互界面实现实时验证与冲突解决。为支持逻辑监督与可解释的社会分析，我们发布了包含160组人际互动及其对应逻辑结构的数据集。实验表明，SymbolicThought在提升标注准确性与一致性的同时，显著降低时间成本，为叙事理解、可解释AI及大模型评估提供实用工具。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。