提出新型树形检索框架，提升跨文档多跳问答效果。
Hierarchical Abstract Tree for Cross-Document Retrieval-Augmented Generation
- 构建自适应层级抽象树，动态融合文档避免分布假设
- 多粒度检索代理使查询重组织，跨文档连接更紧密
- 在多跳问答上超越现有方法，适合复杂知识推理任务
检索增强生成（RAG）通过引入外部知识提升大模型能力，基于树的RAG通过分层索引支持多粒度查询。然而，现有树形RAG方法针对单文档设计，在处理跨文档多跳问题时存在三大挑战：（1）分布适应性差，k-means聚类因固定分布假设引入噪声；（2）结构孤立，树索引缺乏显式跨文档关联；（3）抽象粗略，掩盖细粒度信息。为此，我们提出Ψ-RAG，包含两个核心组件：一是通过迭代“合并与坍缩”过程构建的自适应层级抽象树索引，无需先验分布假设；二是多粒度检索代理，能智能重组织查询并使用代理驱动的混合检索器与知识库交互。Ψ-RAG支持从词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分数相较RAPTOR提升25.9%，较HippoRAG 2提升7.4%。代码已开源：https://github.com/Newiz430/Psi-RAG。
原文摘要 · Abstract (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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。