TreeRAG: Unleashing the Power of Hierarchical Storage for Enhanced Knowledge Retrieval in Long Documents

摘要

When confronting long document information retrieval for Query-Focused Summarization(QFS), Traditional Retrieval-Augmented Generation(RAG) frameworks struggle to retrieve all relevant knowledge points, and the chunking and retrieve strategies of existing frameworks may disrupt the connections between knowledge points and the integrity of the information. To address these issues, we propose \textbf{TreeRAG}, which employs \textbf{Tree-Chunking} for chunking and embedding in a tree-like structure , coupled with "\textbf{root-to-leaves}" and "\textbf{leaf-to-root}" retrieve strategy named \textbf{Bidirectional Traversal Retrieval}. This approach effectively preserves the hierarchical structure among knowledge points and significantly enhances the ability to retrieve while minimizing noise inference. Our experimental results on the \textbf{Finance, Law, and Medical subsets of the Dragonball dataset} demonstrate that \textbf{TreeRAG} achieves significant enhancements in both recall quality and precision compared to traditional and popular existing methods and achieves better performance to corresponding question-answering tasks, marking a new breakthrough in long document knowledge retrieval.