用多智能体框架自动构建中国古代事件分类体系
CHisAgent: A Multi-Agent Framework for Event Taxonomy Construction in Ancient Chinese Cultural Systems
- 分三阶段：自下而上提取、自上而下补全、证据引导增强
- 基于《二十四史》构建涵盖政、军、外交等领域的大规模分类体系
- 支持跨文化对齐，适合历史知识图谱与数字人文研究
尽管大语言模型在诸多任务中表现优异，但在历史与文化推理方面，尤其在非英语语境如中国历史中能力有限。分类体系能有效组织历史知识并提升理解。然而，人工构建分类体系成本高且难扩展。为此，我们提出CHisAgent，一种面向古代中文语境的历史分类体系构建多智能体框架。该框架将分类构建分为三个角色专业化阶段：自下而上的诱导器（Inducer）从原始历史文本中推导初始层级结构；自上而下的扩展器（Expander）利用大模型的世界知识引入缺失的中间概念；证据引导的丰富器（Enricher）整合外部结构化历史资源以确保忠实性。基于《二十四史》，我们构建了一个覆盖政治、军事、外交和社会生活的大型领域感知事件分类体系。大量无参考与有参考评估表明，其结构连贯性与覆盖度显著提升，进一步分析显示该分类体系支持跨文化对齐。
原文摘要 · Abstract (English)
Despite strong performance on many tasks, large language models (LLMs) show limited ability in historical and cultural reasoning, particularly in non-English contexts such as Chinese history. Taxonomic structures offer an effective mechanism to organize historical knowledge and improve understanding. However, manual taxonomy construction is costly and difficult to scale. Therefore, we propose \textbf{CHisAgent}, a multi-agent LLM framework for historical taxonomy construction in ancient Chinese contexts. CHisAgent decomposes taxonomy construction into three role-specialized stages: a bottom-up \textit{Inducer} that derives an initial hierarchy from raw historical corpora, a top-down \textit{Expander} that introduces missing intermediate concepts using LLM world knowledge, and an evidence-guided \textit{Enricher} that integrates external structured historical resources to ensure faithfulness. Using the \textit{Twenty-Four Histories}, we construct a large-scale, domain-aware event taxonomy covering politics, military, diplomacy, and social life in ancient China. Extensive reference-free and reference-based evaluations demonstrate improved structural coherence and coverage, while further analysis shows that the resulting taxonomy supports cross-cultural alignment.
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。