Search Is Not Retrieval: Decoupling Semantic Matching from Contextual Assembly in RAG
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909899656527872 |
|---|---|
| author | Nainwani, Harshit Baban, Hediyeh |
| author_facet | Nainwani, Harshit Baban, Hediyeh |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_04939 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Search Is Not Retrieval: Decoupling Semantic Matching from Contextual Assembly in RAG Nainwani, Harshit Baban, Hediyeh Information Retrieval Artificial Intelligence 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. |
| title | Search Is Not Retrieval: Decoupling Semantic Matching from Contextual Assembly in RAG |
| topic | Information Retrieval Artificial Intelligence |
| url | https://arxiv.org/abs/2511.04939 |