Recent advancements in large language models (LLMs) have shown impressive versatility across various tasks. To eliminate its hallucinations, retrieval-augmented generation (RAG) has emerged as a powerful approach, leveraging external knowledge sources like knowledge graphs (KGs). In this paper, we study the task of KG-driven RAG and propose a novel Similar Graph Enhanced Retrieval-Augmented Generation (SimGRAG) method. It effectively addresses the challenge of aligning query texts and KG structures through a two-stage process: (1) query-to-pattern, which uses an LLM to transform queries into a desired graph pattern, and (2) pattern-to-subgraph, which quantifies the alignment between the pattern and candidate subgraphs using a graph semantic distance (GSD) metric. We also develop an optimized retrieval algorithm that efficiently identifies the top-$k$ subgraphs within 1-second latency on a 10-million-scale KG. Extensive experiments show that SimGRAG outperforms state-of-the-art KG-driven RAG methods in both question answering and fact verification, offering superior plug-and-play usability and scalability.

翻译：近年来，大型语言模型（LLM）在各种任务中展现出卓越的通用能力。为消除其幻觉现象，检索增强生成（RAG）已成为一种有效方法，其通过利用知识图谱（KG）等外部知识源来增强模型性能。本文研究KG驱动的RAG任务，并提出一种新颖的相似图增强检索增强生成（SimGRAG）方法。该方法通过两阶段流程有效解决了查询文本与KG结构对齐的挑战：（1）查询到模式阶段，使用LLM将查询转换为期望的图模式；（2）模式到子图阶段，通过图语义距离（GSD）度量量化模式与候选子图之间的对齐程度。我们还开发了一种优化的检索算法，可在千万级规模的KG上实现1秒延迟内高效检索top-$k$子图。大量实验表明，SimGRAG在问答和事实验证任务上均优于当前最先进的KG驱动RAG方法，同时具备优异的即插即用性和可扩展性。