发表机构
Boston Consulting Group（波士顿咨询集团）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对GraphRAG问题，提出HCG-RAG，用模式约束因果图取代开放式提取，构建紧凑两层图。该方法成本低，答案质量优，在医学等基准测试中表现出色，对比实验显示因果图作为检索过滤器有优势，表明图内容比节点数量更重要。
AI 中文摘要
基于图的检索增强生成（GraphRAG）将答案建立在结构化知识之上，但当前系统会详尽地提取实体和关系，生成的图的大小和构建成本随语料库长度而非查询所需推理而变化。我们引入了HCG-RAG（分层因果图RAG），它用模式约束因果图取代了开放式提取：一个自动化管道将语料库提炼成一个固定的、类型化的因果变量词汇表，并在其上构建一个紧凑的两层图。我们的模式约束图在答案质量上与实体关系基线相当，但成本仅为其几分之一：节点数减少3至20倍，构建时的语言模型调用次数比最依赖语言模型的基线（MS-GraphRAG）少8至135倍，并且图足够紧凑，领域专家可进行审核、纠正和扩展。在医学和临床基准测试中，包括一个经神经学家验证的癫痫数据集，HCG-RAG达到或超过了最佳实体关系系统。一项对比实验将因果图作为结构化检索过滤器分离出来，比仅使用嵌入检索的方法提高了6个百分点。在所有具有可发现分层因果结构的领域中，只有施加了更高层次组织的方法优于扁平实体关系检索，这表明图中放置的内容比其包含的节点数量更重要。
英文摘要
Graph-based retrieval-augmented generation (GraphRAG) grounds answers in structured knowledge, but current systems extract entities and relationships exhaustively, producing graphs whose size and construction cost scale with corpus length rather than with the reasoning a query requires. We introduce HCG-RAG (Hierarchical Causal Graph RAG), which replaces open-ended extraction with schema-constrained causal graphs: an automated pipeline distills a corpus into a fixed, typed vocabulary of causal variables and materializes a compact two-tier graph over it. Our schema-constrained graphs match entity-relation baselines on answer quality at a fraction of the cost: 3-20x fewer nodes, 8x-135x fewer build-time LLM calls than the most LLM-intensive baseline (MS-GraphRAG), and graphs compact enough for a domain expert to audit, correct, and extend. On medical and clinical benchmarks, including a neurologist-validated epilepsy dataset, HCG-RAG matches or exceeds the best entity-relation systems. An ablation isolates the causal graph as a structured retrieval filter, contributing +6 percentage points (pp) over embedding-only retrieval. Across all domains with discoverable hierarchical causal structure, only methods imposing higher-level organization outperform flat entity-relation retrieval, indicating that what is placed in the graph matters more than how many nodes it contains.
Comments26 pages, 6 figures
