ACL Findings2025
TreeRAG: Unleashing the Power of Hierarchical Storage for Enhanced Knowledge Retrieval in Long Documents
Wenyu Tao, Xiaofen Xing, Yirong Chen, Linyi Huang, Xiangmin Xu
Abstract
When confronting long document information retrieval for Query-Focused Summarization(QFS), Traditional Retrieval-Augmented Generation(RAG) frameworks struggle to retrieve all relevant chunks, and the chunking and retrieve strategies of existing frameworks may disrupt the connections between chunks and the integrity of the information. To address these issues, we propose TreeRAG, which employs Tree-Chunking for chunking and embedding in a tree-like structure , coupled with "rootto-leaves" and "leaf-to-roots" retrieve strategy named Bidirectional Traversal Retrieval. This approach effectively preserves the hierarchical structure among chunks and significantly enhances the ability to retrieve while minimizing noise inference. Our experimental results on the Finance, Law, and Medical subsets of the Dragonball dataset demonstrate that 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.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval cites Improving Language Models by Retrieving from Trillions of Tokens
- RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval cites Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
- Improving Language Models by Retrieving from Trillions of Tokens cites Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
Builds on11
- Retrieval-Augmented Generation for Knowledge-Intensive NLP TasksPatrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni et al.NeurIPS 2020 · 19,162 citations
- BERTScore: Evaluating Text Generation with BERTTianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q. Weinberger et al.ICLR 2020 · 8,443 citations
- Improving Language Models by Retrieving from Trillions of TokensSebastian Borgeaud, Arthur Mensch, Jordan Hoffmann, Trevor Cai et al.ICML 2022 · 1,629 citations
- Large Language Models Can Be Easily Distracted by Irrelevant ContextFreda Shi, Xinyun Chen, Kanishka Misra, Nathan Scales et al.ICML 2023 · 970 citations
- RAPTOR: Recursive Abstractive Processing for Tree-Organized RetrievalParth Sarthi, Salman Abdullah, Aditi Tuli, Shubh Khanna et al.ICLR 2024 · 460 citations
Related papers
- SAKI-RAG: Mitigating Context Fragmentation in Long-Document RAG via Sentence-level Attention Knowledge IntegrationWenyu Tao, Xiaofen Xing, Zeliang Li, Xiangmin XuEMNLP 2025
- Momoka-RAG: MCTS-Organized Mapping of Knowledge Associations for Long-Document Retrieval Augmented GenerationWenyu Tao, Xiaofen Xing, Zeliang Li, Xiangmin XuACL Findings 2026
- Hierarchical Abstract Tree for Cross-Document Retrieval Augmented GenerationZiwen Zhao, Menglin YangICML 2026
- BookRAG: A Hierarchical Structure-aware Index-based Approach for Retrieval-Augmented Generation on Complex DocumentsShu Wang, Yingli Zhou, Yixiang FangVLDB 2026 · 16 citations
- Disco-RAG: Discourse-Aware Retrieval-Augmented GenerationDongqi Liu, Hang Ding, Qiming Feng, Xurong Xie et al.ACL 2026
