动态匹配查询与检索器能力，提升问答准确率
R$^3$AG: Retriever Routing for Retrieval-Augmented Generation
- 拆解检索器能力为相关性与生成支持度，动态路由选择
- 对比学习融合文档评估与答案正确性，优化选择策略
- 在多个知识密集型任务中超越单一检索器和现有路由方法
检索增强生成（RAG）已成为知识密集型任务的核心技术。然而，RAG的性能常受限于‘一刀切’的检索范式，因为不同查询对不同检索器有不同偏好。尽管近期路由技术尝试动态选择最优检索器，但通常基于语义相关性进行静态选择，忽略了关键差异：检索到的文档不仅需相关，还需有效支持生成正确答案。为此，我们提出R$^3$AG，一种新型路由框架，显式建模查询与检索器能力间的动态对齐。不同于以往方法，R$^3$AG将检索器能力分解为两个可学习维度：检索质量与生成效用。通过对比学习目标，利用互补监督信号——文档评估与下游答案正确性——捕捉查询特定的偏好变化。在多个知识密集型任务上的大量实验表明，R$^3$AG始终优于最佳单个检索器及最先进的静态路由方法。
原文摘要 · Abstract (English)
Retrieval-augmented generation (RAG) has become a cornerstone for knowledge-intensive tasks. However, the efficacy of RAG is often bottlenecked by the ``one-size-fits-all'' retrieval paradigm, as different queries exhibit distinct preferences for different retrievers. While recent routing techniques attempt to select the optimal retriever dynamically, they typically operate under a ``single and static capability'' assumption, selecting retrievers solely based on semantic relevance. This overlooks a critical distinction in RAG: a retrieved document must not only be relevant but also effectively support the generator in producing correct answers. To address this limitation, we propose R$^3$AG, a novel routing framework that explicitly models the dynamic alignment between queries and retriever capabilities. Unlike previous approaches, R$^3$AG decomposes retriever capability into two learnable dimensions: retrieval quality and generation utility. We employ a contrastive learning objective that leverages complementary supervision signals, \textit{i.e.}, document assessments and downstream answer correctness, to capture query-specific preference shifts. Extensive experiments on several knowledge-intensive tasks show that R$^3$AG consistently outperforms both the best individual retrievers and state-of-the-art static routing methods.
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。