mlsanityData to 14 Oct 2026

Synthesizing Text-to-SQL Data from Weak and Strong LLMs

arXiv 2408.03256 ↗First posted 6 Aug 2024cs.CLcited by 54

Not on the map. Why?

Abstract (arXiv)

The capability gap between open-source and closed-source large language models (LLMs) remains a challenge in text-to-SQL tasks. In this paper, we introduce a synthetic data approach that combines data produced by larger, more powerful models (strong models) with error information data generated by smaller, not well-aligned models (weak models). The method not only enhances the domain generalization of text-to-SQL models but also explores the potential of error data supervision through preference learning. Furthermore, we employ the synthetic data approach for instruction tuning on open-source LLMs, resulting SENSE, a specialized text-to-SQL model. The effectiveness of SENSE is demonstrated through state-of-the-art results on the SPIDER and BIRD benchmarks, bridging the performance gap between open-source models and methods prompted by closed-source models.

Key facts. Cited by 54 papers in the map (data through 14 Oct 2026). Builds on 39 of its 46 references that are in the map. First posted on arXiv 6 Aug 2024.

Builds on

39 of 46 references.

References · 39

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  4. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  5. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  6. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  7. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  8. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,886
  9. 2023Qwen Technical Reportcited by 3,344
  10. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,724
  11. 2023Code Llama: Open Foundation Models for Codecited by 2,139
  12. 2024DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligencecited by 1,181
27 more
  1. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,139
  2. 2023WizardLM: Empowering large pre-trained language models to follow complex instructionscited by 1,125
  3. 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 688
  4. 2017Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learningcited by 687
  5. 2023MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuningcited by 487
  6. 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 477
  7. 2019RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parserscited by 424
  8. 2021PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Modelscited by 411
  9. 2023Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluationcited by 385
  10. 2022UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Modelscited by 231
  11. 2019Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representationcited by 210
  12. 2023RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQLcited by 195
  13. 2020Compositional Generalization and Natural Language Variation: Can a Semantic Parsing Approach Handle Both?cited by 147
  14. 2020Semantic Evaluation for Text-to-SQL with Distilled Test Suitescited by 126
  15. 2020Structure-Grounded Pretraining for Text-to-SQLcited by 126
  16. 2021LGESQL: Line Graph Enhanced Text-to-SQL Model with Mixed Local and Non-Local Relationscited by 119
  17. 2021Towards Robustness of Text-to-SQL Models against Synonym Substitutioncited by 110
  18. 2023Graphix-T5: Mixing Pre-Trained Transformers with Graph-Aware Layers for Text-to-SQL Parsingcited by 93
  19. 2021Exploring Underexplored Limitations of Cross-Domain Text-to-SQL Generalizationcited by 92
  20. 2022RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQLcited by 85
  21. 2019Representing Schema Structure with Graph Neural Networks for Text-to-SQL Parsingcited by 74
  22. 2023Exploring Chain-of-Thought Style Prompting for Text-to-SQLcited by 69
  23. 2020Learning Contextual Representations for Semantic Parsing with Generation-Augmented Pre-Trainingcited by 65
  24. 2023ACT-SQL: In-Context Learning for Text-to-SQL with Automatically-Generated Chain-of-Thoughtcited by 65
  25. 2023How to Prompt LLMs for Text-to-SQL: A Study in Zero-shot, Single-domain, and Cross-domain Settingscited by 58
  26. 2023TAP4LLM: Table Provider on Sampling, Augmenting, and Packing Semi-structured Data for Large Language Model Reasoningcited by 32
  27. 2021Awakening Latent Grounding from Pretrained Language Models for Semantic Parsingcited by 28

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 7; 2025: 29; 2026: 18.

54 papers.

Sort:

By area:

  1. 2024A Survey on Data Synthesis and Augmentation for Large Language Modelscited by 41
  2. 2025XiYan-SQL: A Novel Multi-Generator Framework For Text-to-SQLcited by 40
  3. 2025Arctic-Text2SQL-R1: Simple Rewards, Strong Reasoning in Text-to-SQLcited by 38
  4. 2025SQL-o1: A Self-Reward Heuristic Dynamic Search Method for Text-to-SQLcited by 19
  5. 2025STaR-SQL: Self-Taught Reasoner for Text-to-SQLcited by 17
  6. 2024SQL-GEN: Bridging the Dialect Gap for Text-to-SQL Via Synthetic Data And Model Mergingcited by 16
  7. 2024Balancing Cost and Effectiveness of Synthetic Data Generation Strategies for LLMscited by 15
  8. 2024ROUTE: Robust Multitask Tuning and Collaboration for Text-to-SQLcited by 13
  9. 2025Text2SQL-Flow: A Robust SQL-Aware Data Augmentation Framework for Text-to-SQLcited by 11
  10. 2024Large Language Models are Good Multi-lingual Learners : When LLMs Meet Cross-lingual Promptscited by 10
  11. 2025MTIR-SQL: Multi-turn Tool-Integrated Reasoning Reinforcement Learning for Text-to-SQLcited by 10
  12. 2025BASE-SQL: A powerful open source Text-To-SQL baseline approachcited by 9
38 more
  1. 2025LearNAT: Learning NL2SQL with AST-guided Task Decomposition for Large Language Modelscited by 8
  2. 2025ReEx-SQL: Reasoning with Execution-Aware Reinforcement Learning for Text-to-SQLcited by 8
  3. 2025Graph-Reward-SQL: Execution-Free Reinforcement Learning for Text-to-SQL via Graph Matching and Stepwise Rewardcited by 7
  4. 2025Can LLMs Narrate Tabular Data? An Evaluation Framework for Natural Language Representations of Text-to-SQL System Outputscited by 7
  5. 2024DataGpt-SQL-7B: An Open-Source Language Model for Text-to-SQLcited by 5
  6. 2025Mutual Reinforcement of LLM Dialogue Synthesis and Summarization Capabilities for Few-Shot Dialogue Summarizationcited by 5
  7. 2025DB-Explore: Automated Database Exploration and Instruction Synthesis for Text-to-SQLcited by 5
  8. 2025SPFT-SQL: Enhancing Large Language Model for Text-to-SQL Parsing by Self-Play Fine-Tuningcited by 5
  9. 2025SAFE-SQL: Self-Augmented In-Context Learning with Fine-grained Example Selection for Text-to-SQLcited by 4
  10. 2025JOLT-SQL: Joint Loss Tuning of Text-to-SQL with Confusion-aware Noisy Schema Samplingcited by 4
  11. 2025Exploring the Landscape of Text-to-SQL with Large Language Models: Progresses, Challenges and Opportunitiescited by 4
  12. 2025SEED: Enhancing Text-to-SQL Performance and Practical Usability Through Automatic Evidence Generationcited by 4
  13. 2024Mastering the Craft of Data Synthesis for CodeLLMscited by 3
  14. 2025SQaLe: A Large Text-to-SQL Corpus Grounded in Real Schemascited by 3
  15. 2025SynQuE: Estimating Synthetic Dataset Quality Without Annotationscited by 2
  16. 2025SQLong: Enhanced NL2SQL for Longer Contexts with LLMscited by 1
  17. 2025Distill-C: Enhanced NL2SQL via Distilled Customization with LLMscited by 1
  18. 2025Text-to-SQL Task-oriented Dialogue Ontology Constructioncited by 1
  19. 2025SQLSpace: A Representation Space for Text-to-SQL to Discover and Mitigate Robustness Gapscited by 1
  20. 2026EvolSQL: Structure-Aware Evolution for Scalable Text-to-SQL Data Synthesiscited by 1
  21. 2026Feynman: Knowledge-Infused Diagramming Agent for Scalable Visual Designscited by 1
  22. 2026SQLStructEval: Structural Evaluation of LLM Text-to-SQL Generationcited by 1
  23. 2026Every Step Counts: Step-Level Credit Assignment for Tool-Integrated Text-to-SQLcited by 1
  24. 2026EXPO-SQL: Execution-based Clause-level Policy Optimization for Text-to-SQLcited by 1
  25. 2025UNJOIN: Enhancing Multi-Table Text-to-SQL Generation via Schema Simplificationcited by 0
  26. 2025GradeSQL: Test-Time Inference with Outcome Reward Models for Text-to-SQL Generation from Large Language Modelscited by 0
  27. 2025Do LLMs Align with My Task? Evaluating Text-to-SQL via Dataset Alignmentcited by 0
  28. 2025Skeletons Matter: Dynamic Data Augmentation for Text-to-Querycited by 0
  29. 2025Bridging Global Intent with Local Details: A Hierarchical Representation Approach for Semantic Validation in Text-to-SQLcited by 0
  30. 2026RingSQL: Schema-Independent Synthetic Data Generation for Text-to-SQL Reinforcement Learningcited by 0
  31. 2026SemanticAgent: A Semantics-Aware Framework for Text-to-SQL Data Synthesiscited by 0
  32. 2026LEAF-SQL: Level-wise Exploration with Adaptive Fine-graining for Text-to-SQL Skeleton Predictioncited by 0
  33. 2026Retrieve Only Relevant Tables Whether Few or Many: Adaptive Table Retrieval Methodcited by 0
  34. 2026Residual Skill Optimization for Text-to-SQL Ensemblescited by 0
  35. 2026Knowledge Distillation for Low-Resource Open-source Text-to-SQL Modelcited by 0
  36. 2026SIRIUS-SQL: Anchoring Multi-Candidate Text-to-SQL in Execution Feedbackcited by 0
  37. 2026ZAS-SQL: Distilling Rules from Failures for Zero-Shot Text-to-SQLcited by 0
  38. 2026EvoSQL: Memory-Augmented Critic-Generator Co-Evolution for Text-to-SQLcited by 0

50 most cited of 54 All 54 (JSON)