A Unified Framework for Context-Aware and Relation-Aware Graph Retrieval-Augmented Generation

2026-06-16

AI Summary

Existing Graph Retrieval-Augmented Generation (Graph RAG) approaches struggle to effectively integrate contextual and relational information from both entities and text segments, thereby limiting their capacity to capture emergent knowledge. To address this limitation, this work proposes HyGRAG, a novel framework that unifies contextual and relational modeling through a hybrid hierarchical graph index. HyGRAG leverages iterative clustering and large language models to generate multi-granularity knowledge summaries and introduces a cross-level, context- and relation-aware retrieval mechanism. Notably, it is the first Graph RAG framework to achieve deep fusion of these two types of information and supports dynamic, attachment-based local re-summarization for efficient updates. Experimental results demonstrate that HyGRAG improves average accuracy by 9.7% on multi-hop reasoning tasks while maintaining strong computational efficiency.

Abstract

Retrieval-Augmented Generation (RAG) has emerged as a paradigm for enhancing large language models (LLMs) with external knowledge, yet existing graph-based methods face a fundamental limitation: entity-centric and chunk-centric approaches operate on representations anchored to original text without true knowledge fusion. While entity-centric methods connect logically related content and chunk-centric methods preserve context, both retrieve information separately through similarity search, missing emergent understanding from their synthesis. In this paper, we propose HyGRAG, a hierarchical graph RAG framework that transcends source documents by addressing three core challenges: constructing summaries that genuinely integrate contextual and relational information, leveraging these synthesized representations to access emergent knowledge during retrieval, and efficiently updating hierarchical structures for dynamic corpora. Specifically, we design hierarchical index structures over hybrid graphs with both chunk and entity nodes, then iteratively cluster them and generate LLM-based summaries. Then, we design context and relation-aware retrieval that searches across all abstraction levels while expanding through community membership. Moreover, we enable dynamic knowledge update through attachment-based algorithms with only local re-summarization. Experimental results show that HyGRAG improves the average accuracy of multi-hop reasoning tasks by 9.7%, while maintaining reasonable efficiency.

Problem

• Retrieval-Augmented Generation
• graph-based RAG
• knowledge fusion
• context-aware retrieval
• relation-aware retrieval

Innovation

• Hierarchical Graph RAG
• Context-Aware Retrieval
• Relation-Aware Retrieval
• Dynamic Knowledge Update
• Knowledge Fusion