用知识图谱增强问答，提升大模型答案覆盖率与准确性
KERAG: Knowledge-Enhanced Retrieval-Augmented Generation for Advanced Question Answering
- 通过扩展检索子图获取更多相关知识，突破传统方法覆盖受限
- 在多个基准上比当前最优方案高7%，超越GPT-4o 10-21%
- 适合需要高精度、复杂推理的开放域问答场景
检索增强生成（RAG）通过引入外部数据缓解大语言模型的幻觉问题，其中知识图谱（KG）为问答提供关键信息。传统知识图谱问答方法依赖语义解析，通常仅检索生成答案所必需的知识，因严格模式要求和语义模糊性导致覆盖不足。我们提出KERAG，一种基于知识图谱的新型RAG流程，通过检索更广泛的潜在相关子图提升问答覆盖范围。结合检索-过滤-摘要三阶段策略，并使用微调后的语言模型对知识子图进行链式思维推理，有效降低噪声，提升简单与复杂问题的问答质量。实验表明，KERAG在性能上优于现有最优方案约7%，且在多项指标上超过GPT-4o（Tool）达10%-21%。
原文摘要 · Abstract (English)
Retrieval-Augmented Generation (RAG) mitigates hallucination in Large Language Models (LLMs) by incorporating external data, with Knowledge Graphs (KGs) offering crucial information for question answering. Traditional Knowledge Graph Question Answering (KGQA) methods rely on semantic parsing, which typically retrieves knowledge strictly necessary for answer generation, thus often suffer from low coverage due to rigid schema requirements and semantic ambiguity. We present KERAG, a novel KG-based RAG pipeline that enhances QA coverage by retrieving a broader subgraph likely to contain relevant information. Our retrieval-filtering-summarization approach, combined with fine-tuned LLMs for Chain-of-Thought reasoning on knowledge sub-graphs, reduces noises and improves QA for both simple and complex questions. Experiments demonstrate that KERAG surpasses state-of-the-art solutions by about 7% in quality and exceeds GPT-4o (Tool) by 10-21%.
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。