提出分阶段粗到精检索，提升RAG效率与效果
FunnelRAG: A Coarse-to-Fine Progressive Retrieval Paradigm for RAG
- 构建粗粒度到细粒度的渐进式检索流程
- 检索耗时减少近40%，效果相当
- 适合追求高效RAG系统的开发者
检索增强生成（RAG）在大语言模型中广泛应用，其核心由检索模块（检索器）和生成模块（生成器）组成。生成器的表现高度依赖于检索器的有效性和效率。然而，当前广泛采用的检索范式仍为扁平结构，将检索过程视为一次性、固定粒度的操作。尽管有效，但存在两大局限：(1) 扁平检索对单一检索器造成较大负担；(2) 固定粒度限制了检索性能上限。为此，本文提出一种具有粗到精粒度的渐进式检索范式——FunnelRAG，通过协同粗到精粒度、大到小数量、低到高容量的策略，缓解单个检索器压力并提升检索性能上限。大量实验表明，FunnelRAG在保持相近检索性能的同时，时间开销降低近40%。
原文摘要 · Abstract (English)
Retrieval-Augmented Generation (RAG) prevails in Large Language Models. It mainly consists of retrieval and generation. The retrieval modules (a.k.a. retrievers) aim to find useful information used to facilitate the generation modules (a.k.a. generators). As such, generators' performance largely depends on the effectiveness and efficiency of retrievers. However, the widely used retrieval paradigm remains flat. It treats retrieval procedures as a one-off deal with constant granularity. Despite effectiveness, we argue that they suffer from two limitations: (1) flat retrieval exerts a significant burden on one retriever; (2) constant granularity limits the ceiling of retrieval performance. In this work, we propose a progressive retrieval paradigm with coarse-to-fine granularity for RAG, termed FunnelRAG, so as to balance effectiveness and efficiency. Specifically, FunnelRAG establishes a progressive retrieval pipeline by collaborating coarse-to-fine granularity, large-to-small quantity, and low-to-high capacity, which can relieve the burden on one retriever and also promote the ceiling of retrieval performance. Extensive experiments manifest that FunnelRAG achieves comparable retrieval performance while the time overhead is reduced by nearly 40 percent.
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。