通过轻量路由实现高效联邦检索，降低通信开销同时保持检索精度。
Efficient Federated Search for Retrieval-Augmented Generation using Lightweight Routing
- 基于神经分类器动态选择相关数据源，避免盲目查询。
- 通信量减少80.65%，延迟降低52.50%，效果媲美全源查询。
- 适合需隐私保护的跨机构知识检索场景。
大型语言模型在多个领域表现优异，但仍易产生幻觉和不一致。检索增强生成（RAG）通过从外部来源检索相关文档来增强模型输入，缓解此类问题。在许多现实场景中，相关知识分散于不同组织或机构，促使需要一种联邦搜索机制，在不集中数据的前提下聚合异构数据源的结果。本文提出RAGRoute，一种用于RAG系统的轻量级路由机制，通过神经分类器在查询时动态选择相关数据源，避免无差别查询。该选择性路由显著降低了通信开销和端到端延迟，同时保持了检索质量，在三个基准上分别实现了最高80.65%的通信量减少和52.50%的延迟降低，且检索准确率与查询所有源相当。
原文摘要 · Abstract (English)
Large language models (LLMs) achieve remarkable performance across domains but remain prone to hallucinations and inconsistencies. Retrieval-augmented generation (RAG) mitigates these issues by augmenting model inputs with relevant documents retrieved from external sources. In many real-world scenarios, relevant knowledge is fragmented across organizations or institutions, motivating the need for federated search mechanisms that can aggregate results from heterogeneous data sources without centralizing the data. We introduce RAGRoute, a lightweight routing mechanism for federated search in RAG systems that dynamically selects relevant data sources at query time using a neural classifier, avoiding indiscriminate querying. This selective routing reduces communication overhead and end-to-end latency while preserving retrieval quality, achieving up to 80.65% reductions in communication volume and 52.50% reductions in latency across three benchmarks, while matching the accuracy of querying all sources.
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。