Knowledge Graph-Guided Retrieval Augmented Generation
This work addresses the problem of hallucination in large language models for natural language processing applications, providing a potentially significant improvement for users of these models.
The authors tackled the issue of hallucination in large language models by proposing a Knowledge Graph-Guided Retrieval Augmented Generation framework, resulting in improved diversity and coherence of retrieved results. Extensive experiments on the HotpotQA dataset demonstrated the advantages of this approach over existing methods.
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.