HG-RAG：用于结构化知识图谱的层次引导检索增强生成
HG-RAG: Hierarchy-Guided Retrieval-Augmented Generation for Structured Knowledge Graphs
浏览论文内容
中文总结 AI 辅助
研究针对RAG系统在处理结构化知识推理时的不足，提出HG-RAG框架，通过在层次知识图谱上遍历为语言模型提供结构化上下文，经多规模多类型查询评估，该框架在相关推理任务中优于基线，减少幻觉并保持一致性。
中文摘要 AI 辅助
检索增强生成（RAG）已被证明是一种广泛成功的方法，可提高大语言模型（LLM）输出的质量。然而，RAG系统通常从平面文档存储中检索上下文，当查询需要跨结构化知识进行层次或关系推理时会遇到困难。本文提出了HG-RAG（层次引导的RAG）框架，它在层次知识图谱上执行图遍历，为语言模型提供结构化上下文。检索管道从查询中解析命名实体锚点，然后通过父节点向上扩展上下文，通过关系邻居横向扩展，必要时通过子节点向下扩展。通过在三个世界规模（18 - 800个节点）上针对密集检索基线评估HG-RAG，使用四种查询类型：局部事实、层次、邻域和多跳。结果表明，HG-RAG在层次、关系和多跳推理任务上始终优于平面基线，同时减少幻觉并保持局部一致性。
英文摘要
Retrieval Augmented Generation (RAG) has proven to be a widely successful process at improving the quality of outputs from a Large Language Model (LLM) for wider context. However, RAG systems typically retrieve context from flat document stores, which struggles when queries require hierarchical or relational reasoning across structured knowledge. I present HG-RAG (Hierarchy-Guided RAG), a framework that performs graph-traversal over a hierarchical knowledge graph to deliver structured context to a language model. My retrieval pipeline resolves a named entity anchor from the query, then expands context upward through parent nodes, laterally through relational neighbors, and downward through child nodes when needed. I evaluate HG-RAG against a dense retrieval baseline across three world scales (18-800 nodes) with four query types: local fact, hierarchical, neighborhood, and multi-hop. Results show HG-RAG consistently outperforms the flat baseline on hierarchical, relational, and multi-hop reasoning tasks, while reducing hallucination and maintaining locality coherence.
发表机构
- University of California, Merced（加州大学默塞德分校）
机构由 AI 辅助整理，请以论文原文为准。
