基于历史文本知识图谱的图检索增强生成研究
Research on Graph-Retrieval Augmented Generation Based on Historical Text Knowledge Graphs
AI总结：
针对通用大模型在历史文本分析中的知识缺口，提出Graph RAG框架，结合思维链与图检索增强生成，构建前四史人物关系数据集，提升关系抽取性能并缓解幻觉。
摘要：
本文针对计算人文与AIGC技术背景下，通用大语言模型在历史文本分析中存在的领域知识缺口问题。我们提出了Graph RAG框架，结合思维链提示、自我指令生成和过程监督，以最少的人工标注创建了《前四史》人物关系数据集。该数据集支持自动化历史知识抽取，降低了人工成本。在图增强生成阶段，我们引入了知识图谱与检索增强生成之间的协作机制，提高了通用模型与历史知识的对齐度。实验表明，领域专用模型Xunzi-Qwen1.5-14B在简体中文输入和思维链提示下，在关系抽取任务中取得了最优性能（F1 = 0.68）。集成GraphRAG的DeepSeek模型在开放域C-CLUE关系抽取数据集上，将F1值提升了11%（0.08-0.19），超过了Xunzi-Qwen1.5-14B的F1值（0.12），有效缓解了幻觉现象，并提高了可解释性。该框架为古典文本知识抽取提供了一种低资源解决方案，推进了历史知识服务和人文研究。
英文摘要：
This article addresses domain knowledge gaps in general large language models for historical text analysis in the context of computational humanities and AIGC technology. We propose the Graph RAG framework, combining chain-of-thought prompting, self-instruction generation, and process supervision to create a The First Four Histories character relationship dataset with minimal manual annotation. This dataset supports automated historical knowledge extraction, reducing labor costs. In the graph-augmented generation phase, we introduce a collaborative mechanism between knowledge graphs and retrieval-augmented generation, improving the alignment of general models with historical knowledge. Experiments show that the domain-specific model Xunzi-Qwen1.5-14B, with Simplified Chinese input and chain-of-thought prompting, achieves optimal performance in relation extraction (F1 = 0.68). The DeepSeek model integrated with GraphRAG improves F1 by 11% (0.08-0.19) on the open-domain C-CLUE relation extraction dataset, surpassing the F1 value of Xunzi-Qwen1.5-14B (0.12), effectively alleviating hallucinations phenomenon, and improving interpretability. This framework offers a low-resource solution for classical text knowledge extraction, advancing historical knowledge services and humanities research.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
