OMD-GraphRAG：利用本体引导提取、多维聚类和双通道融合增强GraphRAG
OMD-GraphRAG: Enhancing GraphRAG with Ontology-Guided Extraction, Multi-Dimensional Clustering and Dual-Channel Fusion
AI总结：
提出OMD-GraphRAG框架，通过本体引导知识提取、多维社区聚类和双通道图检索融合，提升GraphRAG在复杂推理和多跳查询中的性能。
摘要：
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重大挑战。尽管现有的GraphRAG框架在结构化知识组织方面取得了进展，但在知识提取精度、社区报告完整性和检索性能方面仍存在局限性。本文提出OMD-GraphRAG，一个基于开源GraphRAG构建的增强框架。该框架引入了三项核心创新：（1）本体引导知识提取，使用预定义Schema指导LLM准确识别领域特定实体和关系；（2）多维社区聚类策略，通过对齐完成、基于属性的聚类和多跳关系聚类提高社区完整性；（3）双通道图检索融合，通过混合图和社区检索平衡问答准确性和性能。在MultiHop-RAG基准上的评估结果显示，OMD-GraphRAG在综合F1分数上优于主流开源解决方案（如LightRAG），特别是在推理和时间查询方面。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
