CHisAgent: A Multi-Agent Framework for Event Taxonomy Construction in Ancient Chinese Cultural Systems

TL;DR

This paper introduces CHisAgent, a multi-agent framework that constructs detailed event taxonomies for ancient Chinese history by combining LLMs with external resources, improving organization and cross-cultural understanding.

Contribution

The paper presents a novel multi-agent LLM framework for scalable, accurate taxonomy construction in ancient Chinese cultural contexts, integrating multiple stages and external knowledge sources.

Findings

Constructed a large-scale event taxonomy covering multiple domains in ancient China.

Demonstrated improved structural coherence and coverage over baseline methods.

Supported cross-cultural alignment with the generated taxonomy.

Abstract

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.