Knowledge Graph-Guided Retrieval Augmented Generation

• DOI: 10.48550/arxiv.2502.06864
• Publication Date: 2025-01-01
• Authors: Zhu, Xiangrong; Xie, Yuexiang; Liu, Yi; Li, Yaliang; Hu, Wei
• Keywords: FOS: Computer and information sciences; Computer Science - Computation and Language; Artificial Intelligence (cs.AI); Computer Science - Artificial Intelligence; Computation and Language (cs.CL)

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.<br/>Accepted in the 2025 Annual Conference of the Nations of the Americas Chapter of the ACL (NAACL 2025)<br/>