UniAI-GraphRAG: Synergizing Ontology-Guided Extraction, Multi-Dimensional Clustering, and Dual-Channel Fusion for Robust Multi-Hop Reasoning

2026-03-26

AI Summary

This work addresses key limitations in existing GraphRAG systems—namely, insufficient multi-hop reasoning capability, poor cross-domain adaptability, incomplete community reports, and suboptimal retrieval performance. To overcome these challenges, we propose an enhanced GraphRAG framework that integrates ontology-guided knowledge extraction (leveraging predefined schemas to constrain large language models in generating structured entity-relation triples), multi-dimensional community clustering (combining node attributes with multi-hop topological information), and a dual-channel graph retrieval fusion mechanism that jointly exploits graph structure and community-level semantics. Evaluated on the MultiHopRAG benchmark, our approach achieves superior overall F1 scores compared to leading open-source alternatives such as LightRAG, demonstrating particularly strong performance on complex reasoning tasks and time-sensitive queries.

Technology Category

• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Knowledge Representation and Reasoning: Ontologies
• Machine Learning: Graph-based Machine Learning

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

Abstract

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 cross-industry adaptability, community report integrity, and retrieval performance. This paper proposes UniAI-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 MultiHopRAG benchmark show that UniAI-GraphRAG outperforms mainstream open source solutions (e.g.LightRAG) in comprehensive F1 scores, particularly in inference and temporal queries. The code is available at https://github.com/UnicomAI/wanwu/tree/main/rag/rag_open_source/rag_core/graph.

Problem

• Retrieval-Augmented Generation
• Multi-Hop Reasoning
• GraphRAG
• Domain-Specific QA
• Knowledge Graph

Innovation

• Ontology-Guided Extraction
• Multi-Dimensional Clustering
• Dual-Channel Fusion
• GraphRAG
• Multi-Hop Reasoning