mlsanityData to 14 Oct 2026

CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databases

arXiv 1909.05378 ↗First posted 11 Sep 2019cs.CL cs.AIcited by 185

Not on the map. Why?

Cited by 20 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We present CoSQL, a corpus for building cross-domain, general-purpose database (DB) querying dialogue systems. It consists of 30k+ turns plus 10k+ annotated SQL queries, obtained from a Wizard-of-Oz (WOZ) collection of 3k dialogues querying 200 complex DBs spanning 138 domains. Each dialogue simulates a real-world DB query scenario with a crowd worker as a user exploring the DB and a SQL expert retrieving answers with SQL, clarifying ambiguous questions, or otherwise informing of unanswerable questions. When user questions are answerable by SQL, the expert describes the SQL and execution results to the user, hence maintaining a natural interaction flow. CoSQL introduces new challenges compared to existing task-oriented dialogue datasets:(1) the dialogue states are grounded in SQL, a domain-independent executable representation, instead of domain-specific slot-value pairs, and (2) because testing is done on unseen databases, success requires generalizing to new domains. CoSQL includes three tasks: SQL-grounded dialogue state tracking, response generation from query results, and user dialogue act prediction. We evaluate a set of strong baselines for each task and show that CoSQL presents significant challenges for future research. The dataset, baselines, and leaderboard will be released at https://yale-lily.github.io/cosql.

Key facts. Cited by 185 papers in the map (data through 14 Oct 2026). First posted on arXiv 11 Sep 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 16; 2022: 32; 2023: 43; 2024: 28; 2025: 26; 2026: 40.

185 papers.

Sort:

By area:

  1. 2023Teaching Large Language Models to Self-Debugcited by 988
  2. 2022CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesiscited by 885
  3. 2021PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Modelscited by 411
  4. 2023InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedbackcited by 238
  5. 2022UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Modelscited by 231
  6. 2024MapCoder: Multi-Agent Code Generation for Competitive Problem Solvingcited by 177
  7. 2024Large Language Models(LLMs) on Tabular Data: Prediction, Generation, and Understanding -- A Surveycited by 159
  8. 2024Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQLcited by 120
  9. 2023A comprehensive evaluation of ChatGPT's zero-shot Text-to-SQL capabilitycited by 119
  10. 2022Natural Language to Code Generation in Interactive Data Science Notebookscited by 87
  11. 2022RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQLcited by 85
  12. 2023Is GPT-4 a Good Data Analyst?cited by 70
38 more
  1. 2024A Survey on Employing Large Language Models for Text-to-SQL Taskscited by 67
  2. 2023ACT-SQL: In-Context Learning for Text-to-SQL with Automatically-Generated Chain-of-Thoughtcited by 65
  3. 2021Few-Shot Bot: Prompt-Based Learning for Dialogue Systemscited by 64
  4. 2024Learning to Clarify: Multi-turn Conversations with Action-Based Contrastive Self-Trainingcited by 57
  5. 2024A Survey of Text-to-SQL in the Era of LLMs: Where are we, and where are we going?cited by 56
  6. 2022Rethinking Explainability as a Dialogue: A Practitioner's Perspectivecited by 52
  7. 2022A Survey on Text-to-SQL Parsing: Concepts, Methods, and Future Directionscited by 52
  8. 2022Recent Advances in Text-to-SQL: A Survey of What We Have and What We Expectcited by 47
  9. 2024StreamBench: Towards Benchmarking Continuous Improvement of Language Agentscited by 47
  10. 2023Enhancing Few-shot Text-to-SQL Capabilities of Large Language Models: A Study on Prompt Design Strategiescited by 45
  11. 2022Neural Approaches to Conversational Information Retrievalcited by 42
  12. 2023SQL-PaLM: Improved Large Language Model Adaptation for Text-to-SQL (extended)cited by 42
  13. 2023Symbol-LLM: Towards Foundational Symbol-centric Interface For Large Language Modelscited by 39
  14. 2024TabSQLify: Enhancing Reasoning Capabilities of LLMs Through Table Decompositioncited by 39
  15. 2022SPACE-3: Unified Dialog Model Pre-training for Task-Oriented Dialog Understanding and Generationcited by 34
  16. 2021NL-EDIT: Correcting semantic parse errors through natural language interactioncited by 33
  17. 2022Calibrated Interpretation: Confidence Estimation in Semantic Parsingcited by 33
  18. 2025CODESIM: Multi-Agent Code Generation and Problem Solving through Simulation-Driven Planning and Debuggingcited by 32
  19. 2024A Survey of Table Reasoning with Large Language Modelscited by 29
  20. 2022SPACE-2: Tree-Structured Semi-Supervised Contrastive Pre-training for Task-Oriented Dialog Understandingcited by 28
  21. 2022Towards Robustness of Text-to-SQL Models Against Natural and Realistic Adversarial Table Perturbationcited by 28
  22. 2023Natural Language Interfaces for Tabular Data Querying and Visualization: A Surveycited by 27
  23. 2022HIE-SQL: History Information Enhanced Network for Context-Dependent Text-to-SQL Semantic Parsingcited by 26
  24. 2021Improving Text-to-SQL with Schema Dependency Learningcited by 25
  25. 2021Dual Reader-Parser on Hybrid Textual and Tabular Evidence for Open Domain Question Answeringcited by 25
  26. 2023Interleaving Pre-Trained Language Models and Large Language Models for Zero-Shot NL2SQL Generationcited by 24
  27. 2021Logic-Consistency Text Generation from Semantic Parsescited by 23
  28. 2022MultiSpider: Towards Benchmarking Multilingual Text-to-SQL Semantic Parsingcited by 22
  29. 2023DialogStudio: Towards Richest and Most Diverse Unified Dataset Collection for Conversational AIcited by 22
  30. 2023Deep Learning for Code Intelligence: Survey, Benchmark and Toolkitcited by 22
  31. 2022UniSAr: A Unified Structure-Aware Autoregressive Language Model for Text-to-SQLcited by 20
  32. 2022N-Best Hypotheses Reranking for Text-To-SQL Systemscited by 19
  33. 2022STAR: SQL Guided Pre-Training for Context-dependent Text-to-SQL Parsingcited by 19
  34. 2023Interactive Text-to-SQL Generation via Editable Step-by-Step Explanationscited by 19
  35. 2024PRACTIQ: A Practical Conversational Text-to-SQL dataset with Ambiguous and Unanswerable Queriescited by 19
  36. 2025BIRD-INTERACT: Re-imagining Text-to-SQL Evaluation for Large Language Models via Lens of Dynamic Interactionscited by 19
  37. 2023Towards Knowledge-Intensive Text-to-SQL Semantic Parsing with Formulaic Knowledgecited by 18
  38. 2024Tapilot-Crossing: Benchmarking and Evolving LLMs Towards Interactive Data Analysis Agentscited by 17

50 most cited of 185 All 185 (JSON)