用知识图谱增强问答系统，提升复杂问题推理能力
OMD-GraphRAG: Enhancing GraphRAG with Ontology-Guided Extraction, Multi-Dimensional Clustering and Dual-Channel Fusion
- 用领域预设结构引导大模型精准提取实体与关系
- 通过多维聚类和双通道检索，显著提升查询准确率
- 适合需要高精度推理的医疗、法律等专业领域应用
检索增强生成（RAG）系统在复杂推理、多跳查询和领域特定问答中面临挑战。现有GraphRAG框架虽在结构化知识组织上取得进展，但在知识提取精度、社区完整性及检索性能方面仍存不足。本文提出OMD-GraphRAG，基于开源GraphRAG框架引入三项核心改进：(1) 领域预设模式引导的大模型知识提取，提升实体与关系识别准确性；(2) 多维社区聚类策略，通过对齐补全、属性聚类与多跳关系聚类提升社区完整性；(3) 双通道图检索融合机制，结合图与社区检索实现问答准确率与效率平衡。在MultiHop-RAG基准测试中，OMD-GraphRAG在综合F1分数上优于主流开源方案（如LightRAG），尤其在推理型和时序型查询任务中表现突出。
原文摘要 · Abstract (English)
Retrieval-Augmented Generation (RAG) systems face significant challenges in complex reasoning, multi-hop queries, and domain-specific QA. While existing GraphRAG frameworks have made progress in structural knowledge organization, they still have limitations in knowledge extraction precision, community report integrity, and retrieval performance. This paper proposes OMD-GraphRAG, an enhanced framework built upon open-source GraphRAG. The framework introduces three core innovations: (1) Ontology-Guided Knowledge Extraction that uses predefined Schema to guide LLMs in accurately identifying domain-specific entities and relations; (2) Multi-Dimensional Community Clustering Strategy that improves community completeness through alignment completion, attribute-based clustering, and multi-hop relationship clustering; (3) Dual-Channel Graph Retrieval Fusion that balances QA accuracy and performance through hybrid graph and community retrieval. Evaluation results on MultiHop-RAG benchmark show that OMD-GraphRAG outperforms mainstream open source solutions (e.g., LightRAG) in comprehensive F1 scores, particularly in inference and temporal queries.
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。