EGREFINE: An Execution-Grounded Optimization Framework for Text-to-SQL Schema Refinement
Not on the map. Why?
Abstract (arXiv)
Text-to-SQL enables non-expert users to query databases in natural language, yet real-world schemas often suffer from ambiguous, abbreviated, or inconsistent naming conventions that degrade model accuracy. Existing approaches treat schemas as fixed and address errors downstream. In this paper, we frame schema refinement as a constrained optimization problem: find a renaming function that maximizes downstream Text-to-SQL execution accuracy while preserving query equivalence through database views. We analyze the computational hardness of this problem, which motivates a column-wise greedy decomposition, and instantiate it as EGRefine: a four-phase pipeline that screens ambiguous columns, generates context-aware candidate names, verifies them through execution-grounded feedback, and materializes the result as non-destructive SQL views. The pipeline carries two structural properties: column-local non-degradation, ensured by the conservative selection rule in the verification phase, and database-level query equivalence, ensured by the view-based materialization phase. Together they make the resulting refinement safe by construction at the column level, with cross-column and prompt-level interactions handled empirically rather than analytically. Across controlled schema-degradation, real-world, and enterprise benchmarks, EGRefine recovers accuracy lost to schema naming noise where applicable and correctly abstains where the underlying task exceeds current Text-to-SQL capabilities, with refined schemas transferring across model families to enable refine-once, serve-many-models deployment. Code and data are publicly available at https://github.com/ai-jiaqian/EGRefine.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 41 of its 50 references that are in the map. First posted on arXiv 1 May 2026.
Builds on
41 of 50 references.
References · 41
- 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
- 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
- 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
- 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,139
- 2023Teaching Large Language Models to Self-Debugcited by 988
- 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 688
- 2017Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learningcited by 687
- 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 477
- 2019RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parserscited by 424
- 2021PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Modelscited by 411
- 2023Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluationcited by 385
- 2022CodeT: Code Generation with Generated Testscited by 384
29 more
- 2024Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflowscited by 232
- 2023RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQLcited by 195
- 2024CodeS: Towards Building Open-source Language Models for Text-to-SQLcited by 187
- 2019CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databasescited by 185
- 2024CHESS: Contextual Harnessing for Efficient SQL Synthesiscited by 169
- 2023C3: Zero-shot Text-to-SQL with ChatGPTcited by 164
- 2023MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQLcited by 164
- 2020Bridging Textual and Tabular Data for Cross-Domain Text-to-SQL Semantic Parsingcited by 133
- 2024Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQLcited by 120
- 2021Towards Robustness of Text-to-SQL Models against Synonym Substitutioncited by 110
- 2021Exploring Underexplored Limitations of Cross-Domain Text-to-SQL Generalizationcited by 92
- 2024The Death of Schema Linking? Text-to-SQL in the Age of Well-Reasoned Language Modelscited by 67
- 2024A Survey of Text-to-SQL in the Era of LLMs: Where are we, and where are we going?cited by 56
- 2023Dr.Spider: A Diagnostic Evaluation Benchmark towards Text-to-SQL Robustnesscited by 53
- 2020Speak to your Parser: Interactive Text-to-SQL with Natural Language Feedbackcited by 44
- 2024BEAVER: An Enterprise Benchmark for Text-to-SQLcited by 42
- 2024AMBROSIA: A Benchmark for Parsing Ambiguous Questions into Database Queriescited by 35
- 2023Benchmarking and Improving Text-to-SQL Generation under Ambiguitycited by 34
- 2023Text-to-SQL Error Correction with Language Models of Codecited by 21
- 2025Reliable Text-to-SQL with Adaptive Abstentioncited by 20
- 2023Interactive Text-to-SQL Generation via Editable Step-by-Step Explanationscited by 19
- 2024PRACTIQ: A Practical Conversational Text-to-SQL dataset with Ambiguous and Unanswerable Queriescited by 19
- 2025SHARE: An SLM-based Hierarchical Action CorREction Assistant for Text-to-SQLcited by 16
- 2024Evaluating the Data Model Robustness of Text-to-SQL Systems Based on Real User Queriescited by 12
- 2025SQL-of-Thought: Multi-agentic Text-to-SQL with Guided Error Correctioncited by 6
- 2025Fundamental Challenges in Evaluating Text2SQL Solutions and Detecting Their Limitationscited by 5
- 2025ODIN: A NL2SQL Recommender to Handle Schema Ambiguitycited by 4
- 2025Interactive Text-to-SQL via Expected Information Gain for Disambiguationcited by 3
- 2025BenchPress: A Human-in-the-Loop Annotation System for Rapid Text-to-SQL Benchmark Curationcited by 3
Built on by
Citing papers per year: 2026: 1.
1 paper.