mlsanityData to 7 Oct 2026

DAC: Decomposed Automation Correction for Text-to-SQL

arXiv 2408.08779 ↗First posted 16 Aug 2024cs.CLcited by 6

Not on the map. Why?

Abstract (arXiv)

Text-to-SQL is an important task that helps people obtain information from databases by automatically generating SQL queries. Considering the brilliant performance, approaches based on Large Language Models (LLMs) become the mainstream for text-to-SQL. Among these approaches, automated correction is an effective approach that further enhances performance by correcting the mistakes in the generated results. The existing correction methods require LLMs to directly correct with generated SQL, while previous research shows that LLMs do not know how to detect mistakes, leading to poor performance. Therefore, in this paper, we propose to employ the decomposed correction to enhance text-to-SQL performance. We first demonstrate that decomposed correction outperforms direct correction since detecting and fixing mistakes with the results of the decomposed sub-tasks is easier than with SQL. Based on this analysis, we introduce Decomposed Automation Correction (DAC), which corrects SQL by decomposing text-to-SQL into entity linking and skeleton parsing. DAC first generates the entity and skeleton corresponding to the question and then compares the differences between the initial SQL and the generated entities and skeleton as feedback for correction. Experimental results show that our method improves performance by 3.7% on average of Spider, Bird, and KaggleDBQA compared with the baseline method, demonstrating the effectiveness of DAC.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 56 of its 66 references that are in the map. First posted on arXiv 16 Aug 2024.

Builds on

56 of 66 references.

References · 56

  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. 2022Training language models to follow instructions with human feedbackcited by 15,712
  4. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  5. 2024DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligencecited by 1,154
  6. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,120
  7. 2023Teaching Large Language Models to Self-Debugcited by 963
  8. 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 667
  9. 2022Decomposed Prompting: A Modular Approach for Solving Complex Taskscited by 554
  10. 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 465
  11. 2019RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parserscited by 420
  12. 2021PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Modelscited by 402
38 more
  1. 2023Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluationcited by 378
  2. 2022CodeT: Code Generation with Generated Testscited by 369
  3. 2023Chain-of-Verification Reduces Hallucination in Large Language Modelscited by 317
  4. 2023A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Modelscited by 244
  5. 2024When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMscited by 230
  6. 2023LEVER: Learning to Verify Language-to-Code Generation with Executioncited by 228
  7. 2019Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representationcited by 210
  8. 2023RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQLcited by 191
  9. 2024CodeS: Towards Building Open-source Language Models for Text-to-SQLcited by 183
  10. 2023MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQLcited by 158
  11. 2024LLM Critics Help Catch LLM Bugscited by 138
  12. 2024Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQLcited by 118
  13. 2021KaggleDBQA: Realistic Evaluation of Text-to-SQL Parserscited by 105
  14. 2024MCS-SQL: Leveraging Multiple Prompts and Multiple-Choice Selection For Text-to-SQL Generationcited by 103
  15. 2024The Dawn of Natural Language to SQL: Are We Fully Ready?cited by 78
  16. 2023LLMs Accelerate Annotation for Medical Information Extractioncited by 77
  17. 2024Self-Contrast: Better Reflection Through Inconsistent Solving Perspectivescited by 71
  18. 2023CodeIE: Large Code Generation Models are Better Few-Shot Information Extractorscited by 67
  19. 2024A Survey on Employing Large Language Models for Text-to-SQL Taskscited by 67
  20. 2024Before Generation, Align it! A Novel and Effective Strategy for Mitigating Hallucinations in Text-to-SQL Generationcited by 49
  21. 2022Recent Advances in Text-to-SQL: A Survey of What We Have and What We Expectcited by 47
  22. 2024DTS-SQL: Decomposed Text-to-SQL with Small Large Language Modelscited by 45
  23. 2019Global Reasoning over Database Structures for Text-to-SQL Parsingcited by 43
  24. 2024FinSQL: Model-Agnostic LLMs-based Text-to-SQL Framework for Financial Analysiscited by 35
  25. 2024Knowledge-to-SQL: Enhancing SQL Generation with Data Expert LLMcited by 35
  26. 2024MAGIC: Generating Self-Correction Guideline for In-Context Text-to-SQLcited by 34
  27. 2024SQLBench: A Comprehensive Evaluation for Text-to-SQL Capabilities of Large Language Modelscited by 32
  28. 2024Decomposition for Enhancing Attention: Improving LLM-based Text-to-SQL through Workflow Paradigmcited by 31
  29. 2021Awakening Latent Grounding from Pretrained Language Models for Semantic Parsingcited by 28
  30. 2023Interleaving Pre-Trained Language Models and Large Language Models for Zero-Shot NL2SQL Generationcited by 24
  31. 2023CRUSH4SQL: Collective Retrieval Using Schema Hallucination For Text2SQLcited by 23
  32. 2023Text-to-SQL Error Correction with Language Models of Codecited by 21
  33. 2023Selective Demonstrations for Cross-domain Text-to-SQLcited by 21
  34. 2022UniSAr: A Unified Structure-Aware Autoregressive Language Model for Text-to-SQLcited by 20
  35. 2023Prompting GPT-3.5 for Text-to-SQL with De-semanticization and Skeleton Retrievalcited by 16
  36. 2024General Purpose Verification for Chain of Thought Promptingcited by 16
  37. 2022Non-Programmers Can Label Programs Indirectly via Active Examples: A Case Study with Text-to-SQLcited by 12
  38. 2023Retrieval-augmented GPT-3.5-based Text-to-SQL Framework with Sample-aware Prompting and Dynamic Revision Chaincited by 12

50 most cited of 56 All 56 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 3.

6 papers.

  1. 2025Understanding, Detecting, and Repairing Real-World In-Context-Learning-Based Text-to-SQL Errorscited by 14
  2. 2025Uncovering the Impact of Chain-of-Thought Reasoning for Direct Preference Optimization: Lessons from Text-to-SQLcited by 9
  3. 2025Exploring the Landscape of Text-to-SQL with Large Language Models: Progresses, Challenges and Opportunitiescited by 4
  4. 2026LEAF-SQL: Level-wise Exploration with Adaptive Fine-graining for Text-to-SQL Skeleton Predictioncited by 0
  5. 2026Integrating Reasoning and Generalization in Text-to-SQL via Self-Enhanced Fine-Tuningcited by 0
  6. 2026ACTS-SQL: Agentic and Critic-Oriented Tree-Structured SQL Correctness with Large Language Modelscited by 0