mlsanityData to 7 Oct 2026

DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction

arXiv 2304.11015 ↗First posted 21 Apr 2023cs.CL cs.AI cs.DBcited by 465

Not on the map. Why?

Cited by 70 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

There is currently a significant gap between the performance of fine-tuned models and prompting approaches using Large Language Models (LLMs) on the challenging task of text-to-SQL, as evaluated on datasets such as Spider. To improve the performance of LLMs in the reasoning process, we study how decomposing the task into smaller sub-tasks can be effective. In particular, we show that breaking down the generation problem into sub-problems and feeding the solutions of those sub-problems into LLMs can be an effective approach for significantly improving their performance. Our experiments with three LLMs show that this approach consistently improves their simple few-shot performance by roughly 10%, pushing the accuracy of LLMs towards SOTA or surpassing it. On the holdout test set of Spider, the SOTA, in terms of execution accuracy, was 79.9 and the new SOTA at the time of this writing using our approach is 85.3. Our approach with in-context learning beats many heavily fine-tuned models by at least 5%. Additionally, when evaluated on the BIRD benchmark, our approach achieved an execution accuracy of 55.9%, setting a new SOTA on its holdout test set.

Key facts. Cited by 465 papers in the map (data through 7 Oct 2026). Builds on 42 of its 80 references that are in the map. First posted on arXiv 21 Apr 2023.

Builds on

42 of 80 references.

References · 42

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  4. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  5. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  6. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  7. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,747
  8. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  9. 2022Emergent Abilities of Large Language Modelscited by 2,483
  10. 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,222
  11. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,397
  12. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,120
30 more
  1. 2022Automatic Chain of Thought Prompting in Large Language Modelscited by 684
  2. 2017Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learningcited by 679
  3. 2022Decomposed Prompting: A Modular Approach for Solving Complex Taskscited by 554
  4. 2020TAPAS: Weakly Supervised Table Parsing via Pre-trainingcited by 432
  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. 2020TaBERT: Pretraining for Joint Understanding of Textual and Tabular Datacited by 395
  8. 2019Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representationcited by 210
  9. 2020GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsingcited by 171
  10. 2016Language to Logical Form with Neural Attentioncited by 158
  11. 2017SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learningcited by 135
  12. 2020Semantic Evaluation for Text-to-SQL with Distilled Test Suitescited by 123
  13. 2021LGESQL: Line Graph Enhanced Text-to-SQL Model with Mixed Local and Non-Local Relationscited by 119
  14. 2023A comprehensive evaluation of ChatGPT's zero-shot Text-to-SQL capabilitycited by 118
  15. 2022Large Language Models are few(1)-shot Table Reasonerscited by 116
  16. 2022Evaluating the Text-to-SQL Capabilities of Large Language Modelscited by 101
  17. 2020SmBoP: Semi-autoregressive Bottom-up Semantic Parsingcited by 97
  18. 2023Graphix-T5: Mixing Pre-Trained Transformers with Graph-Aware Layers for Text-to-SQL Parsingcited by 93
  19. 2019A Comprehensive Exploration on WikiSQL with Table-Aware Word Contextualizationcited by 88
  20. 2022RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQLcited by 85
  21. 2021Natural SQL: Making SQL Easier to Infer from Natural Language Specificationscited by 66
  22. 2020RYANSQL: Recursively Applying Sketch-based Slot Fillings for Complex Text-to-SQL in Cross-Domain Databasescited by 63
  23. 2022A Survey on Text-to-SQL Parsing: Concepts, Methods, and Future Directionscited by 51
  24. 2021SADGA: Structure-Aware Dual Graph Aggregation Network for Text-to-SQLcited by 43
  25. 2021SeaD: End-to-end Text-to-SQL Generation with Schema-aware Denoisingcited by 27
  26. 2022Importance of Synthesizing High-quality Data for Text-to-SQL Parsingcited by 27
  27. 2021Improving Text-to-SQL with Schema Dependency Learningcited by 25
  28. 2022N-Best Hypotheses Reranking for Text-To-SQL Systemscited by 19
  29. 2021Relation Aware Semi-autoregressive Semantic Parsing for NL2SQLcited by 8
  30. 2023Few-Shot Table-to-Text Generation with Prompt Planning and Knowledge Memorizationcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 42; 2024: 142; 2025: 137; 2026: 144.

465 papers.

Sort:

By area:

  1. 2023DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelinescited by 803
  2. 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 667
  3. 2023Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluationcited by 378
  4. 2024Optimizing Instructions and Demonstrations for Multi-Stage Language Model Programscited by 270
  5. 2024Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflowscited by 223
  6. 2024CodeS: Towards Building Open-source Language Models for Text-to-SQLcited by 183
  7. 2024CHESS: Contextual Harnessing for Efficient SQL Synthesiscited by 164
  8. 2023C3: Zero-shot Text-to-SQL with ChatGPTcited by 159
  9. 2023MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQLcited by 158
  10. 2024Large Language Models(LLMs) on Tabular Data: Prediction, Generation, and Understanding -- A Surveycited by 157
  11. 2023Domain Specialization as the Key to Make Large Language Models Disruptive: A Comprehensive Surveycited by 134
  12. 2024CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQLcited by 132
38 more
  1. 2024Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQLcited by 118
  2. 2024MCS-SQL: Leveraging Multiple Prompts and Multiple-Choice Selection For Text-to-SQL Generationcited by 103
  3. 2025OmniSQL: Synthesizing High-quality Text-to-SQL Data at Scalecited by 90
  4. 2023Data-Copilot: Bridging Billions of Data and Humans with Autonomous Workflowcited by 76
  5. 2024TableLLM: Enabling Tabular Data Manipulation by LLMs in Real Office Usage Scenarioscited by 76
  6. 2024EHRAgent: Code Empowers Large Language Models for Few-shot Complex Tabular Reasoning on Electronic Health Recordscited by 75
  7. 2024BLADE: Benchmarking Language Model Agents for Data-Driven Sciencecited by 72
  8. 2023Exploring Chain-of-Thought Style Prompting for Text-to-SQLcited by 69
  9. 2024TableGPT2: A Large Multimodal Model with Tabular Data Integrationcited by 69
  10. 2024A Survey on Employing Large Language Models for Text-to-SQL Taskscited by 67
  11. 2024The Death of Schema Linking? Text-to-SQL in the Age of Well-Reasoned Language Modelscited by 67
  12. 2023ACT-SQL: In-Context Learning for Text-to-SQL with Automatically-Generated Chain-of-Thoughtcited by 65
  13. 2024Retrieval Augmented Generation (RAG) and Beyond: A Comprehensive Survey on How to Make your LLMs use External Data More Wiselycited by 65
  14. 2023Towards Better Chain-of-Thought Prompting Strategies: A Surveycited by 62
  15. 2023Unifying the Perspectives of NLP and Software Engineering: A Survey on Language Models for Codecited by 62
  16. 2025Reasoning-SQL: Reinforcement Learning with SQL Tailored Partial Rewards for Reasoning-Enhanced Text-to-SQLcited by 59
  17. 2023How to Prompt LLMs for Text-to-SQL: A Study in Zero-shot, Single-domain, and Cross-domain Settingscited by 57
  18. 2023TPTU: Large Language Model-based AI Agents for Task Planning and Tool Usagecited by 54
  19. 2024A Survey of Text-to-SQL in the Era of LLMs: Where are we, and where are we going?cited by 54
  20. 2024Synthesizing Text-to-SQL Data from Weak and Strong LLMscited by 53
  21. 2024Large Language Model for Table Processing: A Surveycited by 52
  22. 2024RSL-SQL: Robust Schema Linking in Text-to-SQL Generationcited by 51
  23. 2025OpenSearch-SQL: Enhancing Text-to-SQL with Dynamic Few-shot and Consistency Alignmentcited by 51
  24. 2024Before Generation, Align it! A Novel and Effective Strategy for Mitigating Hallucinations in Text-to-SQL Generationcited by 49
  25. 2023Skill-Based Few-Shot Selection for In-Context Learningcited by 46
  26. 2024DTS-SQL: Decomposed Text-to-SQL with Small Large Language Modelscited by 45
  27. 2024Why Larger Language Models Do In-context Learning Differently?cited by 44
  28. 2023SQL-PaLM: Improved Large Language Model Adaptation for Text-to-SQL (extended)cited by 42
  29. 2024TableRAG: Million-Token Table Understanding with Language Modelscited by 40
  30. 2025XiYan-SQL: A Novel Multi-Generator Framework For Text-to-SQLcited by 40
  31. 2024Middleware for LLMs: Tools Are Instrumental for Language Agents in Complex Environmentscited by 39
  32. 2024TabSQLify: Enhancing Reasoning Capabilities of LLMs Through Table Decompositioncited by 39
  33. 2024Fine-Tuning and Prompt Optimization: Two Great Steps that Work Better Togethercited by 38
  34. 2024BEAVER: An Enterprise Benchmark for Text-to-SQLcited by 37
  35. 2024FinSQL: Model-Agnostic LLMs-based Text-to-SQL Framework for Financial Analysiscited by 35
  36. 2024Knowledge-to-SQL: Enhancing SQL Generation with Data Expert LLMcited by 35
  37. 2024E-SQL: Direct Schema Linking via Question Enrichment in Text-to-SQLcited by 35
  38. 2024PURPLE: Making a Large Language Model a Better SQL Writercited by 34

50 most cited of 465 All 465 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026Integrating Reasoning and Generalization in Text-to-SQL via Self-Enhanced Fine-Tuning
  2. 2024RB-SQL: A Retrieval-based LLM Framework for Text-to-SQL
  3. 2025SQLForge: Synthesizing Reliable and Diverse Data to Enhance Text-to-SQL Reasoning in LLMs
  4. 2026Test-Time Verification for Text-to-SQL via Outcome Reward Models
  5. 2025STaR-SQL: Self-Taught Reasoner for Text-to-SQL
  6. 2026ACTS-SQL: Agentic and Critic-Oriented Tree-Structured SQL Correctness with Large Language Models
  7. 2024Lucy: Think and Reason to Solve Text-to-SQL
  8. 2025Arctic-Text2SQL-R1: Simple Rewards, Strong Reasoning in Text-to-SQL