arXiv:2610.01767 · RAG 检索增强
A Matryoshka Hierarchical RAG for Efficient Multi-Hop Question Answering
用于高效多跳问答的 Matryoshka 分层 RAG
A Matryoshka Hierarchical RAG for Efficient Multi-Hop Question Answering
- 类型：arxiv
- 标识：2610.01767
- 链接：http://arxiv.org/abs/2610.01767v1
- 主分类：rag
- 形态：method
- TLDR：Retrieval-Augmented Generation (RAG) systems for multi-hop Question Answering (QA) must balance retrieval quality with computational cost. This cost is incurred during indexing time, through the use of expensive Knowledge Graphs (KGs) or Large Language Models (LLMs) to generate summaries, or during querying, through iterative LLM-driven retrieval. To reduce it while maintaining retrieval quality, we present MatRAG, a hierarchical framework that combines RAG systems with Matryoshka Representation Learning (MRL). MatRAG addresses both kinds of cost by aligning the semantic hierarchy of a cluster
- 待LLM分类：否
- 标题中文：用于高效多跳问答的 Matryoshka 分层 RAG
- TLDR中文：用于多跳问答（QA）的检索增强生成（RAG）系统需在检索质量与计算成本之间取得平衡。该成本既产生于索引阶段——使用昂贵的知识图谱（KGs）或大语言模型（LLMs）生成摘要，也产生于查询阶段——通过 LLM 驱动的迭代检索。为在保持检索质量的同时降低成本，我们提出 MatRAG——一个将 RAG 系统与 Matryoshka 表示学习（MRL）相结合的分层框架。MatRAG 通过对齐聚类的语义层次……
- 来源文件：
- /inbox/tom/_candidates/2026-10-03-agent-rag-longcontext-candidates.json