解决图检索生成中噪声多、依赖外部知识过强的问题
Empowering GraphRAG with Knowledge Filtering and Integration
- 两阶段过滤机制剔除无关信息，提升检索质量
- 基于逻辑值的选择策略平衡外部知识与模型内生推理
- 在多个基线模型上显著提升知识问答性能
近年来，大语言模型（LLMs）推动了自然语言处理的发展，但常面临知识盲区和幻觉问题。图检索增强生成（GraphRAG）通过整合外部知识图谱的结构化知识来增强模型推理能力。然而，我们识别出两个关键挑战：(1) 检索到的信息噪声大且不相关，会降低性能；(2) 过度依赖外部知识会抑制模型自身的推理能力。为此，我们提出 GraphRAG-FI（Filtering and Integration），包含 GraphRAG-Filtering 和 GraphRAG-Integration 两部分。GraphRAG-Filtering 采用两阶段过滤机制，对检索信息进行精炼；GraphRAG-Integration 则通过基于逻辑值的选择策略，平衡来自 GraphRAG 的外部知识与 LLM 内生推理能力，减轻对检索结果的过度依赖。在知识图谱问答任务上的实验表明，GraphRAG-FI 在多个骨干模型上均显著提升了推理性能，构建了一个更可靠、高效的 GraphRAG 框架。
原文摘要 · Abstract (English)
In recent years, large language models (LLMs) have revolutionized the field of natural language processing. However, they often suffer from knowledge gaps and hallucinations. Graph retrieval-augmented generation (GraphRAG) enhances LLM reasoning by integrating structured knowledge from external graphs. However, we identify two key challenges that plague GraphRAG:(1) Retrieving noisy and irrelevant information can degrade performance and (2)Excessive reliance on external knowledge suppresses the model's intrinsic reasoning. To address these issues, we propose GraphRAG-FI (Filtering and Integration), consisting of GraphRAG-Filtering and GraphRAG-Integration. GraphRAG-Filtering employs a two-stage filtering mechanism to refine retrieved information. GraphRAG-Integration employs a logits-based selection strategy to balance external knowledge from GraphRAG with the LLM's intrinsic reasoning,reducing over-reliance on retrievals. Experiments on knowledge graph QA tasks demonstrate that GraphRAG-FI significantly improves reasoning performance across multiple backbone models, establishing a more reliable and effective GraphRAG framework.
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。