RetrievalRouter: Joint Modality and Architecture Selection for Document Retrieval

  • 类型:arxiv
  • 标识:2608.25625
  • 链接:https://arxiv.org/abs/2608.25625
  • 主分类:rag
  • 形态:method
  • 被引:0
  • 被引来源:Semantic Scholar
  • S2被引:0
  • 影响力被引:0
  • TLDR:RetrievalRouter is a lightweight query-aware router that learns, from the query text alone, which retrieval pipeline best fits each query, and achieves significantly higher nDCG@5 across accuracy-oriented settings, while matching or numerically outperforming them on both nDCG@5 and latency in latency-oriented settings.
  • 待LLM分类:否
  • 标题中文:RetrievalRouter:面向文档检索的模态与架构联合选择
  • TLDR中文:RetrievalRouter 是一种轻量级 query-aware router,仅依据 query 文本即可学习最匹配的检索 pipeline,在面向准确率的设置下 nDCG@5 显著更高,而在面向延迟的设置下,nDCG@5 和延迟均匹配或数值上优于基线。
  • 来源文件:
  • /inbox/tom/_candidates/2026-08-27-agent-rag-longcontext-candidates.json
  • /inbox/tom/_candidates/2026-08-28-agent-rag-longcontext-candidates.json
  • [S2 enrich]