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

arXiv:2601.05520v2 Announce Type: replace 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 extbf{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 extit{Inducer} that derives an initial hierarchy from raw historical corpora, a top-down extit{Expander} that introduces missing intermediate concepts using LLM world knowledge, and an evidence-guided extit{Enricher} that integrates external structured historical resources to ensure faithfulness. Using the extit{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.

Related

• From National Curricula to Cultural Awareness: Constructing Open-Ended Culture-Specific Question Answering Dataset
• Beyond tokens: a unified framework for latent communication in LLM-based multi-agent systems
• Toward Culturally Aligned LLMs through Ontology-Guided Multi-Agent Reasoning
• Mitigating Cross-Lingual Cultural Inconsistencies in LLMs via Consensus-Driven Preference Optimisation

Source: arXiv cs.CL | 2026-09-03