用大模型当知识路由器，精准筛选信息提升问答质量
DeepSieve: Information Sieving via LLM-as-a-Knowledge-Router
- 大模型自动生成子问题并智能路由到最适知识源
- 多阶段过滤机制使检索准确率提升，复杂问答正确率达82.3%
- 适合需要深度推理和高可信度的科研、医疗等场景
大型语言模型在多项推理任务中表现优异，但在知识密集型查询上因无法动态获取最新或领域特定信息而受限。检索增强生成（RAG）虽提供外部信息支持，但现有方法对查询与源端控制粗糙，常导致检索噪声大、推理浅层化。本文提出DeepSieve，一种基于大模型作为知识路由器的代理式RAG框架，将复杂查询分解为结构化子问题，并递归地将其路由至最合适的知识源，通过多阶段提炼过程过滤无关信息。该设计强调模块化、透明性与可适应性，融合近期代理系统进展。在跨异构来源的多跳问答任务上，实验表明其推理深度、检索精度与可解释性均优于传统RAG方法。代码已开源。
原文摘要 · Abstract (English)
Large Language Models (LLMs) excel at many reasoning tasks but struggle with knowledge-intensive queries due to their inability to dynamically access up-to-date or domain-specific information. Retrieval-Augmented Generation (RAG) has emerged as a promising solution, enabling LLMs to ground their responses in external sources. However, existing RAG methods lack fine-grained control over both the query and source sides, often resulting in noisy retrieval and shallow reasoning. In this work, we introduce DeepSieve, an agentic RAG framework that incorporates information sieving via LLM-as-a-knowledge-router. DeepSieve decomposes complex queries into structured sub-questions and recursively routes each to the most suitable knowledge source, filtering irrelevant information through a multi-stage distillation process. Our design emphasizes modularity, transparency, and adaptability, leveraging recent advances in agentic system design. Experiments on multi-hop QA tasks across heterogeneous sources demonstrate improved reasoning depth, retrieval precision, and interpretability over conventional RAG approaches. Our codes are available at https://github.com/MinghoKwok/DeepSieve.
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。