用知识图谱增强大模型问答，让检索结果更连贯、多样。
Knowledge Graph-Guided Retrieval Augmented Generation
- 基于语义检索种子片段，再用知识图谱扩展并组织相关知识
- 在HotpotQA上显著提升回答质量和检索效果
- 适合需要准确推理和结构化知识的问答系统研究者
检索增强生成（RAG）是缓解大语言模型幻觉问题的有前景技术。现有研究多采用语义方法检索孤立的相关片段，忽视其内在关联。本文提出知识图谱引导的检索增强生成框架KG²RAG，利用知识图谱（KG）揭示片段间的事实级关系，提升检索结果的多样性与连贯性。具体而言，在语义检索获得初始片段后，KG²RAG通过知识图谱引导的片段扩展与基于知识图谱的片段组织，输出结构清晰、信息丰富的段落。在HotpotQA及其变体数据集上的大量实验表明，相比现有RAG方法，KG²RAG在响应质量与检索质量上均具优势。
原文摘要 · Abstract (English)
Retrieval-augmented generation (RAG) has emerged as a promising technology for addressing hallucination issues in the responses generated by large language models (LLMs). Existing studies on RAG primarily focus on applying semantic-based approaches to retrieve isolated relevant chunks, which ignore their intrinsic relationships. In this paper, we propose a novel Knowledge Graph-Guided Retrieval Augmented Generation (KG$^2$RAG) framework that utilizes knowledge graphs (KGs) to provide fact-level relationships between chunks, improving the diversity and coherence of the retrieved results. Specifically, after performing a semantic-based retrieval to provide seed chunks, KG$^2$RAG employs a KG-guided chunk expansion process and a KG-based chunk organization process to deliver relevant and important knowledge in well-organized paragraphs. Extensive experiments conducted on the HotpotQA dataset and its variants demonstrate the advantages of KG$^2$RAG compared to existing RAG-based approaches, in terms of both response quality and retrieval quality.
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。