搜索并非检索：RAG中语义匹配与上下文组装的解耦
Search Is Not Retrieval: Decoupling Semantic Matching from Contextual Assembly in RAG
AI总结：
针对现有RAG检索系统混淆相关信息查找与推理上下文供给的问题，提出SINR双层解耦框架，在无额外开销下提升检索性能，为下一代检索增强AI系统提供基础。
摘要：
检索系统是当代人工智能流水线的核心组成部分，但多数系统混淆了两个独立过程：查找相关信息、为推理提供充足上下文。我们提出Search-Is-Not-Retrieve（SINR，搜索非检索）框架，这是一种区分细粒度搜索表示与粗粒度检索上下文的双层架构。SINR通过将语义精准的小型搜索块直接连接到上下文完整的大型检索块，在不产生额外处理开销的前提下，提升了检索系统的可组合性、可扩展性与上下文保真度。该设计将检索从被动步骤转变为主动步骤，使系统架构更贴近人类处理信息的方式。我们阐述了SINR框架的概念基础、形式化结构、实现问题与定性结果，为下一代采用检索机制的人工智能系统提供了实用基础。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
