ArchRAG: Attributed Community-based Hierarchical Retrieval-Augmented Generation
This work addresses the problem of efficient knowledge integration for large language models, particularly for question-answer tasks, which is significant for natural language processing applications.
The authors tackled the issue of inefficient retrieval in graph-based Retrieval-Augmented Generation (RAG) approaches, resulting in improved accuracy and reduced token cost. ArchRAG outperforms existing methods, although specific numbers are not provided.
Retrieval-Augmented Generation (RAG) has proven effective in integrating external knowledge into large language models (LLMs) for solving question-answer (QA) tasks. The state-of-the-art RAG approaches often use the graph data as the external data since they capture the rich semantic information and link relationships between entities. However, existing graph-based RAG approaches cannot accurately identify the relevant information from the graph and also consume large numbers of tokens in the online retrieval process. To address these issues, we introduce a novel graph-based RAG approach, called Attributed Community-based Hierarchical RAG (ArchRAG), by augmenting the question using attributed communities, and also introducing a novel LLM-based hierarchical clustering method. To retrieve the most relevant information from the graph for the question, we build a novel hierarchical index structure for the attributed communities and develop an effective online retrieval method. Experimental results demonstrate that ArchRAG outperforms existing methods in both accuracy and token cost.