用检索增强生成构建文档级知识图谱，解决长文本遗忘与实体消歧难题。
RAKG:Document-level Retrieval Augmented Knowledge Graph Construction
- 以预实体为查询做RAG，缓解大模型长文本遗忘问题。
- 在MINE数据集上准确率达95.91%，比基线高6.2个百分点。
- 适合需要高精度知识图谱构建的科研与企业应用。
随着基于知识图谱的检索增强生成（RAG）技术（如GraphRAG和Pike-RAG）的发展，知识图谱在提升大语言模型（LLMs）推理能力方面愈发重要。然而，传统知识图谱构建（KGC）方法面临实体消歧复杂、模式定义僵化、跨文档知识融合不足等问题。本文聚焦于自动文档级知识图谱构建任务，提出文档级检索增强知识图谱构建（RAKG）框架。RAKG从文本块中提取预实体，并将其作为RAG的查询，有效缓解了大模型的长上下文遗忘问题，降低了共指消解复杂度。相比传统方法，RAKG更有效地捕捉全局信息及节点间的关联，提升了模型整体性能。此外，将RAG评估框架引入KGC领域，通过筛选与评估生成的知识图谱，避免了由大模型幻觉导致的错误实体与关系。我们还构建了MINE数据集，为每篇论文建立标准知识图谱，并实验验证了RAKG性能。结果表明，RAKG在MINE数据集上准确率达到95.91%，较当前最佳基线GraphRAG（89.71%）提升6.2个百分点。代码已开源：https://github.com/LMMApplication/RAKG。
原文摘要 · Abstract (English)
With the rise of knowledge graph based retrieval-augmented generation (RAG) techniques such as GraphRAG and Pike-RAG, the role of knowledge graphs in enhancing the reasoning capabilities of large language models (LLMs) has become increasingly prominent. However, traditional Knowledge Graph Construction (KGC) methods face challenges like complex entity disambiguation, rigid schema definition, and insufficient cross-document knowledge integration. This paper focuses on the task of automatic document-level knowledge graph construction. It proposes the Document-level Retrieval Augmented Knowledge Graph Construction (RAKG) framework. RAKG extracts pre-entities from text chunks and utilizes these pre-entities as queries for RAG, effectively addressing the issue of long-context forgetting in LLMs and reducing the complexity of Coreference Resolution. In contrast to conventional KGC methods, RAKG more effectively captures global information and the interconnections among disparate nodes, thereby enhancing the overall performance of the model. Additionally, we transfer the RAG evaluation framework to the KGC field and filter and evaluate the generated knowledge graphs, thereby avoiding incorrectly generated entities and relationships caused by hallucinations in LLMs. We further developed the MINE dataset by constructing standard knowledge graphs for each article and experimentally validated the performance of RAKG. The results show that RAKG achieves an accuracy of 95.91 % on the MINE dataset, a 6.2 % point improvement over the current best baseline, GraphRAG (89.71 %). The code is available at https://github.com/LMMApplication/RAKG.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。