用知识图谱增强大模型问答，让答案更准确可信。
Knowledge Graph-extended Retrieval Augmented Generation for Question Answering
- 结合大模型与知识图谱，无需训练即可跨图谱适配。
- 多跳问题准确率提升，单跳性能略有下降。
- 适合需要可解释性问答的场景，如医疗、法律。
大语言模型（LLMs）和知识图谱（KGs）为鲁棒且可解释的问答提供了前景。虽然大模型擅长自然语言理解，但存在知识缺失和幻觉问题；而知识图谱虽具结构化知识，却缺乏自然语言交互能力。本文提出一种无需训练的融合系统，将二者结合，实现对缺失事实的鲁棒性与自然语言交互的便捷性。该方法属于一种基于知识图谱的检索增强生成（KG-RAG），包含问题分解模块以提升多跳信息检索与答案可解释性。通过上下文学习（ICL）与思维链（CoT）提示，生成独立处理的显式推理链，提高答案真实性。在MetaQA基准测试中，多跳问题准确率提升，单跳性能相较基线略有下降。结果表明，KG-RAG能通过融合非结构化语言理解与结构化知识检索，增强问答系统的透明性。
原文摘要 · Abstract (English)
Large Language Models (LLMs) and Knowledge Graphs (KGs) offer a promising approach to robust and explainable Question Answering (QA). While LLMs excel at natural language understanding, they suffer from knowledge gaps and hallucinations. KGs provide structured knowledge but lack natural language interaction. Ideally, an AI system should be both robust to missing facts as well as easy to communicate with. This paper proposes such a system that integrates LLMs and KGs without requiring training, ensuring adaptability across different KGs with minimal human effort. The resulting approach can be classified as a specific form of a Retrieval Augmented Generation (RAG) with a KG, thus, it is dubbed Knowledge Graph-extended Retrieval Augmented Generation (KG-RAG). It includes a question decomposition module to enhance multi-hop information retrieval and answer explainability. Using In-Context Learning (ICL) and Chain-of-Thought (CoT) prompting, it generates explicit reasoning chains processed separately to improve truthfulness. Experiments on the MetaQA benchmark show increased accuracy for multi-hop questions, though with a slight trade-off in single-hop performance compared to LLM with KG baselines. These findings demonstrate KG-RAG's potential to improve transparency in QA by bridging unstructured language understanding with structured knowledge retrieval.
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。