用关键概念筛选文档，大幅降低知识图谱构建成本。
Graph-Guided Concept Selection for Efficient Retrieval-Augmented Generation
- 基于重要概念筛选文档块，减少LLM调用次数
- 在降低90%以上构建成本下保持检索效果
- 适合需高效知识增强的医疗、法律等专业领域
基于图的检索增强生成（RAG）通过从文本块构建知识图谱（KG）来提升大语言模型（LLM）问答中的检索效果，尤其适用于生物医学、法律和政治科学等需多跳推理的领域。然而，此类方法需大量LLM调用从文本块中提取实体与关系，规模化时成本过高。通过细致的消融实验，我们发现某些词语（称为概念）及其关联文档更为关键。据此提出图引导的概念选择方法（G2ConS），核心包括：一种不依赖LLM的文档块选择机制，用于降低知识图谱构建成本；以及一个无需额外调用的独立概念图，用于填补因块筛选导致的知识空白。在多个真实数据集上的评估表明，G2ConS在构建成本、检索有效性和回答质量上均优于所有基线方法。
原文摘要 · Abstract (English)
Graph-based RAG constructs a knowledge graph (KG) from text chunks to enhance retrieval in Large Language Model (LLM)-based question answering. It is especially beneficial in domains such as biomedicine, law, and political science, where effective retrieval often involves multi-hop reasoning over proprietary documents. However, these methods demand numerous LLM calls to extract entities and relations from text chunks, incurring prohibitive costs at scale. Through a carefully designed ablation study, we observe that certain words (termed concepts) and their associated documents are more important. Based on this insight, we propose Graph-Guided Concept Selection (G2ConS). Its core comprises a chunk selection method and an LLM-independent concept graph. The former selects salient document chunks to reduce KG construction costs; the latter closes knowledge gaps introduced by chunk selection at zero cost. Evaluations on multiple real-world datasets show that G2ConS outperforms all baselines in construction cost, retrieval effectiveness, and answering quality.
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。