{
  "annotation_id": "fc4f72c8-d082-4099-9c23-e09948a8881e",
  "date_created": "2026-02-17T05:53:07.765000Z",
  "date_modified": "2026-02-17T05:53:07.765000Z",
  "file_hash": "54432c24e75ea0b23890ab3b52b4b7c8ae769e372d8d34da73fa6e8206cfc91c",
  "private": false,
  "record": {
    "abstract": "Natural language to SQL translation (Text-to-SQL) is one of the long-standing problems that has recently benefited from advances in Large Language Models (LLMs). While most academic Text-to-SQL benchmarks request schema description as a part of natural language input, enterprise-scale applications often require table retrieval before SQL query generation. To address this need, we propose a novel hybrid Retrieval Augmented Generation (RAG) system consisting of contextual, structural, and relational retrieval (CSR-RAG) to achieve computationally efficient yet sufficiently accurate retrieval for enterprise-scale databases. Through extensive enterprise benchmarks, we demonstrate that CSR-RAG achieves up to 40% precision and over 80% recall while incurring a negligible average query generation latency of only 30ms on commodity data center hardware, which makes it appropriate for modern LLM-based enterprise-scale systems.",
    "arxiv_id": "2601.06564",
    "authors": [
      "Rajpreet Singh",
      "Novak Bo\u0161kov",
      "Lawrence Drabeck",
      "Aditya Gudal",
      "Manzoor A. Khan"
    ],
    "categories": [
      "cs.CL"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "title": "CSR-RAG: An Efficient Retrieval System for Text-to-SQL on the Enterprise Scale",
    "url": "https://arxiv.org/abs/2601.06564",
    "version": "v1"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "dc490b72-8a71-41b1-8f91-c182565ac768",
    "id": "arXiv Dataset",
    "type": "Model",
    "variant": "snapshot-2026-01-17",
    "version": "0.1.0"
  },
  "user_id": 1000002
}