CHisAgent: A Multi-Agent Framework for Event Taxonomy Construction in Ancient Chinese Cultural Systems
This addresses the challenge of scalable historical knowledge organization for researchers in Chinese history, though it is incremental as it adapts existing multi-agent methods to a specific domain.
The authors tackled the problem of constructing event taxonomies for ancient Chinese cultural systems, which is costly manually, by proposing CHisAgent, a multi-agent LLM framework that decomposes the task into specialized stages and uses the Twenty-Four Histories to build a large-scale taxonomy, resulting in improved structural coherence and coverage as shown in evaluations.
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.