跨文档检索增强生成的分层摘要树

摘要

检索增强生成（RAG）通过外部知识增强大语言模型能力，基于树结构的RAG将文档组织为层次化索引以支持多粒度查询。然而，现有面向单文档检索的树状RAG方法在扩展至跨文档多跳问答时面临关键挑战：（1）分布适应性差，k均值聚类因刚性分布假设引入噪声；（2）结构孤立性，树状索引缺乏显式跨文档关联；（3）抽象粒度粗糙，模糊细粒度细节。为解决这些局限，我们提出Ψ-RAG框架，其核心包含两个组件：首先是通过迭代式"合并-坍缩"构建的分层抽象树索引，无需先验假设即可自适应数据分布；其次是多粒度检索代理，能通过重组查询和代理驱动的混合检索器与知识库智能交互。Ψ-RAG支持从词元级问答到文档级摘要的多样化任务。在跨文档多跳问答基准测试中，其平均F1分数较RAPTOR提升25.9%，较HippoRAG 2提升7.4%。代码详见https://github.com/Newiz430/Psi-RAG。

English

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.

跨文档检索增强生成的分层摘要树

Hierarchical Abstract Tree for Cross-Document Retrieval-Augmented Generation

摘要

Support