CHisAgent: A Multi-Agent Framework for Event Taxonomy Construction in Ancient Chinese Cultural Systems
cs.CL
Submitted: 2026-01-09
Updated: 2026-10-07
Comments: EMNLP 2026 findings
Code: https://github.com/tangxuemei1995/Ancient-chinese-segmenter
License: http://creativecommons.org/licenses/by-sa/4.0/
The gist: 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.
Terminology
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 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 Inducer that derives an initial hierarchy from raw historical corpora, a top-down Expander that introduces missing intermediate concepts using LLM world knowledge, and an evidence-guided Enricher that integrates external structured historical resources to ensure faithfulness. Using the 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.
Sources
- An Investigation into Value Misalignment in LLM-Generated Texts for Cultural Heritage
- BERTopic: Neural topic modeling with a class-based TF-IDF procedure
- TaxoAdapt: Aligning LLM-Based Multidimensional Taxonomy Construction to Evolving Research Corpora
- Building Data-Driven Occupation Taxonomies: A Bottom-Up Multi-Stage Approach via Semantic Clustering and Multi-Agent Collaboration
- Reference-Free Evaluation of Taxonomies
- Chain-of-Layer: Iteratively Prompting Large Language Models for Taxonomy Induction from Limited Examples
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering