分离搜索与检索，让大模型更精准地组合信息。
Search Is Not Retrieval: Decoupling Semantic Matching from Contextual Assembly in RAG
- 用双层结构区分细粒度搜索和粗粒度上下文
- 信息组合更准确，且不增加计算开销
- 适合需要高精度上下文的智能问答系统
检索系统是现代AI流程的核心，但多数系统混淆了两个独立过程：找到相关资讯，以及提供足够的推理上下文。本文提出Search-Is-Not-Retrieve（SINR）框架，采用双层架构，将细粒度的搜索表示与粗粒度的检索上下文相分离。SINR通过直接连接小而语义准确的搜索块与大而上下文完整的检索块，提升了系统的可组合性、可扩展性和上下文保真度，且无需额外处理成本。该设计使检索从被动步骤变为主动过程，更接近人类的信息处理方式。文章讨论了SINR的概念基础、形式结构、实现问题及定性结果，为下一代基于检索的AI系统提供了实用基础。
原文摘要 · Abstract (English)
Retrieval systems are essential to contemporary AI pipelines, although most confuse two separate processes: finding relevant information and giving enough context for reasoning. We introduce the Search-Is-Not-Retrieve (SINR) framework, a dual-layer architecture that distinguishes between fine-grained search representations and coarse-grained retrieval contexts. SINR enhances the composability, scalability, and context fidelity of retrieval systems by directly connecting small, semantically accurate search chunks to larger, contextually complete retrieve chunks, all without incurring extra processing costs. This design changes retrieval from a passive step to an active one, making the system architecture more like how people process information. We discuss the SINR framework's conceptual foundation, formal structure, implementation issues, and qualitative outcomes. This provides a practical foundation for the next generation of AI systems that use retrieval.
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。