mlsanityData to 7 Oct 2026

RingSQL: Schema-Independent Synthetic Data Generation for Text-to-SQL Reinforcement Learning

arXiv 2601.05451 ↗First posted 9 Jan 2026cs.LG cs.CLcited by 0

On the map: Synthetic data and self-improvement for LLMs → Synthetic reasoning data and bootstrapping

Abstract (arXiv)

Recent advances in text-to-SQL have been driven by larger models, better datasets, and new training methods like RLVR. However, progress remains limited by scarce high-quality training data, a problem RLVR is especially sensitive to since noisy data can produce spurious rewards. Manual data creation is expensive, and existing synthetic methods trade off reliability for scalability: template-based approaches guarantee correct SQL but need schema-specific templates and lack diversity, while LLM-based generation scales easily but lacks quality guarantees. We introduce RingSQL, a hybrid framework for generating question-SQL pairs that combines schema-independent query templates with LLM-based paraphrasing of natural language questions. By grounding question generation in complete template questions, RingSQL preserves question-query correctness across all levels of query complexity, a property purely LLM-based methods fail to maintain. RingSQL also produces the only synthetic dataset that improves RLVR training performance across all tested model architectures and benchmarks, achieving 69.8% average accuracy and surpassing both the next-best synthetic dataset by 2.1% and human-annotated data from Spider and BIRD. Code and data are available at https://github.com/nu-c3lab/RingSQL.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Synthetic reasoning data and bootstrapping, one of 13 directions in Synthetic data and self-improvement for LLMs. Builds on 40 of its 51 references that are in the map. First posted on arXiv 9 Jan 2026.

Builds on

40 of 51 references.

References · 40

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  3. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  4. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,120
  5. 2017Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learningcited by 679
  6. 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 667
  7. 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 465
  8. 2019RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parserscited by 420
  9. 2021PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Modelscited by 402
  10. 2023Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluationcited by 378
  11. 2022Towards a Unified Multi-Dimensional Evaluator for Text Generationcited by 264
  12. 2024Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflowscited by 223
28 more
  1. 2023RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQLcited by 191
  2. 2020GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsingcited by 171
  3. 2024CHESS: Contextual Harnessing for Efficient SQL Synthesiscited by 164
  4. 2024CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQLcited by 132
  5. 2020Structure-Grounded Pretraining for Text-to-SQLcited by 126
  6. 2021Towards Robustness of Text-to-SQL Models against Synonym Substitutioncited by 110
  7. 2023Graphix-T5: Mixing Pre-Trained Transformers with Graph-Aware Layers for Text-to-SQL Parsingcited by 93
  8. 2021Exploring Underexplored Limitations of Cross-Domain Text-to-SQL Generalizationcited by 92
  9. 2025OmniSQL: Synthesizing High-quality Text-to-SQL Data at Scalecited by 90
  10. 2019Text-to-SQL Generation for Question Answering on Electronic Medical Recordscited by 76
  11. 2020Grounded Adaptation for Zero-shot Executable Semantic Parsingcited by 76
  12. 2018SyntaxSQLNet: Syntax Tree Networks for Complex and Cross-DomainText-to-SQL Taskcited by 74
  13. 2024A Survey on Employing Large Language Models for Text-to-SQL Taskscited by 67
  14. 2025SQL-R1: Training Natural Language to SQL Reasoning Model By Reinforcement Learningcited by 67
  15. 2025Reasoning-SQL: Reinforcement Learning with SQL Tailored Partial Rewards for Reasoning-Enhanced Text-to-SQLcited by 59
  16. 2024Synthesizing Text-to-SQL Data from Weak and Strong LLMscited by 53
  17. 2021Learning to Synthesize Data for Semantic Parsingcited by 41
  18. 2025Arctic-Text2SQL-R1: Simple Rewards, Strong Reasoning in Text-to-SQLcited by 38
  19. 2024FinSQL: Model-Agnostic LLMs-based Text-to-SQL Framework for Financial Analysiscited by 35
  20. 2025ReFoRCE: A Text-to-SQL Agent with Self-Refinement, Consensus Enforcement, and Column Explorationcited by 34
  21. 2021Data Augmentation with Hierarchical SQL-to-Question Generation for Cross-domain Text-to-SQL Parsingcited by 32
  22. 2018Question Generation from SQL Queries Improves Neural Semantic Parsingcited by 29
  23. 2024Large Language Model Enhanced Text-to-SQL Generation: A Surveycited by 24
  24. 2025Text2SQL-Flow: A Robust SQL-Aware Data Augmentation Framework for Text-to-SQLcited by 11
  25. 2024BookSQL: A Large Scale Text-to-SQL Dataset for Accounting Domaincited by 10
  26. 2025SQLForge: Synthesizing Reliable and Diverse Data to Enhance Text-to-SQL Reasoning in LLMscited by 10
  27. 2023Lightweight Knowledge Representations for Automating Data Analysiscited by 2
  28. 2024Satyrn: A Platform for Analytics Augmented Generationcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025GradeSQL: Test-Time Inference with Outcome Reward Models for Text-to-SQL Generation from Large Language Models
  2. 2025SING-SQL: A Synthetic Data Generation Framework for In-Domain Text-to-SQL Translation
  3. 2024Balancing Cost and Effectiveness of Synthetic Data Generation Strategies for LLMs
  4. 2025Synthetic Data Generation Using Large Language Models: Advances in Text and Code
  5. 2025SLM-SQL: An Exploration of Small Language Models for Text-to-SQL
  6. 2025Reinforcing Code Generation: Improving Text-to-SQL with Execution-Based Learning
  7. 2025Webscale-RL: Automated Data Pipeline for Scaling RL Data to Pretraining Levels
  8. 2025CogniSQL-R1-Zero: Lightweight Reinforced Reasoning for Efficient SQL Generation