mlsanityData to 7 Oct 2026

DRL: A Deterministic Relational Middleware Layer for Transaction-Safe Enterprise NL2SQL Under Schema-Graph Scaling

arXiv 2608.26172 ↗First posted 23 Jul 2026cs.DB cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Deploying natural-language interfaces over enterprise OLTP catalogs fails at scale because semantic parsers collapse under schema-graph scaling, inflating context beyond stable LLM attention budgets. We present DRL (Deterministic Relational Middleware Layer), a safe pipeline interposing between front-ends and SQL backends. DRL comprises dynamic context pruning, relational AST typing, and transactional safeguard verification (EXPLAIN gating and NULL guards) to bound context and flag operational silent divergence (SDop). We evaluate DRL on PostgreSQL and MySQL, contributing (i) an OLTP schema-graph scaling model, (ii) a 1,000-pair Workload Verification Suite, (iii) baselines B0-B3, and (iv) an enterprise NL2SQL failure taxonomy. On PostgreSQL, schema-linked hints (B1) yield a 76% context reduction over naive full-catalog prompting (B0); DRL's dynamic router (B2) reaches a 92% reduction at pruning p95 = 0.58 ms and middleware p95 = 4.6 ms. GPT-4o, Claude Sonnet 4.5, and Gemini 2.5 Flash achieve 52.9%, 52.8%, and 52.1% execution match under a corrected evaluation harness; SDop flags 89-100% of false-positive EX-passing queries. GPT-4o failures are dominated by semantic/filter errors (254/471), while column hallucination is a minor factor (47/471). Crucially, a single regex defect in our evaluation post-processor silently suppressed accuracy and manufactured a false 4-10% cross-vendor gap that vanished when corrected, showing that benchmark code deserves the same scrutiny as the models it scores. DRL reframes enterprise NL2SQL as systems engineering - context bounding, verification, and plan-aware admission - not a leaderboard exercise.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 27 of its 42 references that are in the map. First posted on arXiv 23 Jul 2026.

Builds on

27 of 42 references.

References · 27

  1. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,120
  2. 2017Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learningcited by 679
  3. 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 667
  4. 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 465
  5. 2019RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parserscited by 420
  6. 2021PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Modelscited by 402
  7. 2022UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Modelscited by 231
  8. 2024Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflowscited by 223
  9. 2019Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representationcited by 210
  10. 2023RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQLcited by 191
  11. 2019CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databasescited by 180
  12. 2019SParC: Cross-Domain Semantic Parsing in Contextcited by 141
15 more
  1. 2018Improving Text-to-SQL Evaluation Methodologycited by 133
  2. 2020Semantic Evaluation for Text-to-SQL with Distilled Test Suitescited by 123
  3. 2021LGESQL: Line Graph Enhanced Text-to-SQL Model with Mixed Local and Non-Local Relationscited by 119
  4. 2021KaggleDBQA: Realistic Evaluation of Text-to-SQL Parserscited by 105
  5. 2020SmBoP: Semi-autoregressive Bottom-up Semantic Parsingcited by 97
  6. 2018TRANX: A Transition-based Neural Abstract Syntax Parser for Semantic Parsing and Code Generationcited by 88
  7. 2019Editing-Based SQL Query Generation for Cross-Domain Context-Dependent Questionscited by 80
  8. 2023Dr.Spider: A Diagnostic Evaluation Benchmark towards Text-to-SQL Robustnesscited by 50
  9. 2019Global Reasoning over Database Structures for Text-to-SQL Parsingcited by 43
  10. 2023EHRSQL: A Practical Text-to-SQL Benchmark for Electronic Health Recordscited by 42
  11. 2022S2SQL: Injecting Syntax to Question-Schema Interaction Graph Encoder for Text-to-SQL Parserscited by 41
  12. 2019A Comparative Survey of Recent Natural Language Interfaces for Databasescited by 33
  13. 2020IGSQL: Database Schema Interaction Graph Based Neural Model for Context-Dependent Text-to-SQL Generationcited by 29
  14. 2022Towards Robustness of Text-to-SQL Models Against Natural and Realistic Adversarial Table Perturbationcited by 28
  15. 2023Divide and Prompt: Chain of Thought Prompting for Text-to-SQLcited by 20

Built on by

Not cited yet.