mlsanityData to 7 Oct 2026

Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning

arXiv 1709.00103 ↗First posted 31 Aug 2017cs.CL cs.AIcited by 679

Not on the map. Why?

Cited by 70 in LLM reasoning, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

A significant amount of the world's knowledge is stored in relational databases. However, the ability for users to retrieve facts from a database is limited due to a lack of understanding of query languages such as SQL. We propose Seq2SQL, a deep neural network for translating natural language questions to corresponding SQL queries. Our model leverages the structure of SQL queries to significantly reduce the output space of generated queries. Moreover, we use rewards from in-the-loop query execution over the database to learn a policy to generate unordered parts of the query, which we show are less suitable for optimization via cross entropy loss. In addition, we will publish WikiSQL, a dataset of 80654 hand-annotated examples of questions and SQL queries distributed across 24241 tables from Wikipedia. This dataset is required to train our model and is an order of magnitude larger than comparable datasets. By applying policy-based reinforcement learning with a query execution environment to WikiSQL, our model Seq2SQL outperforms attentional sequence to sequence models, improving execution accuracy from 35.9% to 59.4% and logical form accuracy from 23.4% to 48.3%.

Key facts. Cited by 679 papers in the map (data through 7 Oct 2026). First posted on arXiv 31 Aug 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 87; 2022: 81; 2023: 123; 2024: 145; 2025: 149; 2026: 94.

679 papers.

Sort:

By area:

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  2. 2023WebArena: A Realistic Web Environment for Building Autonomous Agentscited by 1,908
  3. 2023AgentBench: Evaluating LLMs as Agentscited by 1,211
  4. 2024Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMscited by 822
  5. 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 667
  6. 2024Large Language Models: A Surveycited by 506
  7. 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 465
  8. 2021MetaICL: Learning to Learn In Contextcited by 450
  9. 2024Safety Alignment Should Be Made More Than Just a Few Tokens Deepcited by 450
  10. 2023TinyStories: How Small Can Language Models Be and Still Speak Coherent English?cited by 425
  11. 2021TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Financecited by 402
  12. 2023Augmented Language Models: a Surveycited by 398
38 more
  1. 2023Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluationcited by 378
  2. 2022Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoningcited by 347
  3. 2022CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learningcited by 342
  4. 2023StructGPT: A General Framework for Large Language Model to Reason over Structured Datacited by 339
  5. 2024What matters when building vision-language models?cited by 321
  6. 2024LoRA Learns Less and Forgets Lesscited by 313
  7. 2022UL2: Unifying Language Learning Paradigmscited by 292
  8. 2022Quark: Controllable Text Generation with Reinforced Unlearningcited by 236
  9. 2024ReFT: Reasoning with Reinforced Fine-Tuningcited by 236
  10. 2021TAPEX: Table Pre-training via Learning a Neural SQL Executorcited by 233
  11. 2022UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Modelscited by 231
  12. 2023InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedbackcited by 229
  13. 2023LEVER: Learning to Verify Language-to-Code Generation with Executioncited by 228
  14. 2022Binding Language Models in Symbolic Languagescited by 224
  15. 2024Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflowscited by 223
  16. 2021A Survey of Human-in-the-loop for Machine Learningcited by 214
  17. 2023Evaluating Large Language Models: A Comprehensive Surveycited by 200
  18. 2023RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQLcited by 191
  19. 2023Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoningcited by 177
  20. 2021FeTaQA: Free-form Table Question Answeringcited by 174
  21. 2023SantaCoder: don't reach for the stars!cited by 169
  22. 2024Building and better understanding vision-language models: insights and future directionscited by 169
  23. 2024Large Language Models(LLMs) on Tabular Data: Prediction, Generation, and Understanding -- A Surveycited by 157
  24. 2021CrossFit: A Few-shot Learning Challenge for Cross-task Generalization in NLPcited by 142
  25. 2023TableLlama: Towards Open Large Generalist Models for Tablescited by 136
  26. 2023NL4Opt Competition: Formulating Optimization Problems Based on Their Natural Language Descriptionscited by 133
  27. 2022MultiPL-E: A Scalable and Extensible Approach to Benchmarking Neural Code Generationcited by 132
  28. 2024TableBench: A Comprehensive and Complex Benchmark for Table Question Answeringcited by 127
  29. 2022MultiHiertt: Numerical Reasoning over Multi Hierarchical Tabular and Textual Datacited by 120
  30. 2021LGESQL: Line Graph Enhanced Text-to-SQL Model with Mixed Local and Non-Local Relationscited by 119
  31. 2023Hypothesis Search: Inductive Reasoning with Language Modelscited by 119
  32. 2024Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQLcited by 118
  33. 2021HiTab: A Hierarchical Table Dataset for Question Answering and Natural Language Generationcited by 117
  34. 2022Large Language Models are few(1)-shot Table Reasonerscited by 116
  35. 2021Towards Robustness of Text-to-SQL Models against Synonym Substitutioncited by 110
  36. 2021Case-based Reasoning for Natural Language Queries over Knowledge Basescited by 107
  37. 2021KaggleDBQA: Realistic Evaluation of Text-to-SQL Parserscited by 105
  38. 2024SpreadsheetBench: Towards Challenging Real World Spreadsheet Manipulationcited by 100

50 most cited of 679 All 679 (JSON)