Knowledge Graph Retrieval-Augmented Generation via GNN-Guided Prompting

Haochen Liu, Song Wang, Jundong Li

Keywords: Knowledge Graph, Retrieval-Augmented Generation, Question Answering, Large Language Model, Prompt

TL;DR: We propose GGR, a GNN-guided KG-RAG framework that enhances LLM retrieval in KG-RAG by incorporating GNN Guidance to preserve key reasoning paths and improve relation selection.

Abstract: Large Language Models (LLMs) have demonstrated remarkable performance in open-domain question answering (QA), but their reliance on knowledge learned during pretraining limits their ability to provide accurate and up-to-date information. Knowledge Graph Retrieval-Augmented Generation (KG-RAG) enhances LLMs by incorporating structured knowledge from knowledge graphs (KGs). A common approach in KG-RAG is to retrieve relevant knowledge paths starting from entities in the input question and expanding along KG edges by LLM reasoning. However, existing KG-RAG methods suffer from the challenge that retrieval is performed step by step greedily using only local graph context, which can lead to retrieval errors that prematurely discard essential paths. To address the issue and perform more accurate retrieval, we propose GGR (GNN-Guided Retrieval for LLM Reasoning), a novel GNN-enhanced KG-RAG framework that integrates graph-based relevance scoring into the retrieval process. Our approach computes global importance scores across a contextualized subgraph, ensuring that key reasoning knowledge paths are preserved, even if their local relevance appears weak. Additionally, we introduce local semantic alignment by incorporating query-relation semantic similarity, refining the relation selection of LLM. Extensive experiments on Question-Answering tasks demonstrate that our method significantly improves retrieval accuracy and answer quality, demonstrating the effectiveness of combining graph-based reasoning and LLM-driven retrieval for structured knowledge integration.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the COLM Code of Ethics on https://colmweb.org/CoE.html

Author Guide: I certify that this submission complies with the submission instructions as described on https://colmweb.org/AuthorGuide.html

Submission Number: 557