| title | Hierarchical Abstract Tree for Cross-Document Retrieval-Augmented Generation |
|---|---|
| authors | Ziwen Zhao, Menglin Yang |
| date | 2026-05-01 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2605.00529 |
| upvotes | 5 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | Retrieval-augmented generation (RAG) enhances large language models with external knowledge, and tree-based RAG organizes documents into hierarchical indexes to support queries at multiple granularities. However, existing Tree-RAG methods designed for single-document retrieval face critical challenges in scaling to cross-document multi-hop questions: (1) poor distribution adaptability, where k-means clustering introduces noise due to rigid distribution assumptions; (2) structural isolation, as tree indexes lack explicit cross-document connections; and (3) coarse abstraction, which obscures fine-grained details. To address these limitations, we propose Ψ-RAG, a tree-RAG framework with two key components. First, a hierarchical abstract tree index built through an iterative "merging and collapse" process that adapts to data distributions without a priori assumption. Second, a multi-granular retrieval agent that intelligently interacts with the knowledge base with reorganized queries and an agent-powered hybrid retriever. Ψ-RAG supports diverse tasks from token-level question answering to document-level summarization. On cross-document multi-hop QA benchmarks, it outperforms RAPTOR by 25.9% and HippoRAG 2 by 7.4% in average F1 score. Code is available at https://github.com/Newiz430/Psi-RAG. |
cite
@misc{zhao2026hierarchical,
title={Hierarchical Abstract Tree for Cross-Document Retrieval-Augmented Generation},
author={Ziwen Zhao and Menglin Yang},
year={2026},
eprint={2605.00529},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2605.00529}
}