mlsanityData to 7 Oct 2026

MCS-SQL: Leveraging Multiple Prompts and Multiple-Choice Selection For Text-to-SQL Generation

arXiv 2405.07467 ↗First posted 13 May 2024cs.CLcited by 103

Not on the map. Why?

Abstract (arXiv)

Recent advancements in large language models (LLMs) have enabled in-context learning (ICL)-based methods that significantly outperform fine-tuning approaches for text-to-SQL tasks. However, their performance is still considerably lower than that of human experts on benchmarks that include complex schemas and queries, such as BIRD. This study considers the sensitivity of LLMs to the prompts and introduces a novel approach that leverages multiple prompts to explore a broader search space for possible answers and effectively aggregate them. Specifically, we robustly refine the database schema through schema linking using multiple prompts. Thereafter, we generate various candidate SQL queries based on the refined schema and diverse prompts. Finally, the candidate queries are filtered based on their confidence scores, and the optimal query is obtained through a multiple-choice selection that is presented to the LLM. When evaluated on the BIRD and Spider benchmarks, the proposed method achieved execution accuracies of 65.5% and 89.6%, respectively, significantly outperforming previous ICL-based methods. Moreover, we established a new SOTA performance on the BIRD in terms of both the accuracy and efficiency of the generated queries.

Key facts. Cited by 103 papers in the map (data through 7 Oct 2026). Builds on 26 of its 51 references that are in the map. First posted on arXiv 13 May 2024.

Builds on

26 of 51 references.

References · 26

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  3. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  4. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  5. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,397
  6. 2021Calibrate Before Use: Improving Few-Shot Performance of Language Modelscited by 1,371
  7. 2021What Makes Good In-Context Examples for GPT-3?cited by 1,184
  8. 2021Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivitycited by 1,122
  9. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,120
  10. 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 667
  11. 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 465
  12. 2023Large Language Models Are Not Robust Multiple Choice Selectorscited by 454
14 more
  1. 2023Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluationcited by 378
  2. 2021Do Prompt-Based Models Really Understand the Meaning of their Prompts?cited by 324
  3. 2023Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicinecited by 319
  4. 2023Large Language Models Sensitivity to The Order of Options in Multiple-Choice Questionscited by 249
  5. 2019Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representationcited by 210
  6. 2023RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQLcited by 191
  7. 2023C3: Zero-shot Text-to-SQL with ChatGPTcited by 159
  8. 2022Self-Adaptive In-Context Learning: An Information Compression Perspective for In-Context Example Selection and Orderingcited by 158
  9. 2023Graphix-T5: Mixing Pre-Trained Transformers with Graph-Aware Layers for Text-to-SQL Parsingcited by 93
  10. 2022RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQLcited by 85
  11. 2023Exploring Chain-of-Thought Style Prompting for Text-to-SQLcited by 69
  12. 2023Evaluating Cross-Domain Text-to-SQL Models and Benchmarkscited by 32
  13. 2021SeaD: End-to-end Text-to-SQL Generation with Schema-aware Denoisingcited by 27
  14. 2023Prompting GPT-3.5 for Text-to-SQL with De-semanticization and Skeleton Retrievalcited by 16

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 19; 2025: 54; 2026: 30.

103 papers.

Sort:

By area:

  1. 2024CHESS: Contextual Harnessing for Efficient SQL Synthesiscited by 164
  2. 2024CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQLcited by 132
  3. 2024Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQLcited by 118
  4. 2025OmniSQL: Synthesizing High-quality Text-to-SQL Data at Scalecited by 90
  5. 2024TableGPT2: A Large Multimodal Model with Tabular Data Integrationcited by 69
  6. 2024A Survey on Employing Large Language Models for Text-to-SQL Taskscited by 67
  7. 2024The Death of Schema Linking? Text-to-SQL in the Age of Well-Reasoned Language Modelscited by 67
  8. 2025Reasoning-SQL: Reinforcement Learning with SQL Tailored Partial Rewards for Reasoning-Enhanced Text-to-SQLcited by 59
  9. 2024A Survey of Text-to-SQL in the Era of LLMs: Where are we, and where are we going?cited by 54
  10. 2024RSL-SQL: Robust Schema Linking in Text-to-SQL Generationcited by 51
  11. 2025OpenSearch-SQL: Enhancing Text-to-SQL with Dynamic Few-shot and Consistency Alignmentcited by 51
  12. 2025XiYan-SQL: A Novel Multi-Generator Framework For Text-to-SQLcited by 40
38 more
  1. 2024E-SQL: Direct Schema Linking via Question Enrichment in Text-to-SQLcited by 35
  2. 2024MAGIC: Generating Self-Correction Guideline for In-Context Text-to-SQLcited by 34
  3. 2025Is Long Context All You Need? Leveraging LLM's Extended Context for NL2SQLcited by 30
  4. 2025LinkAlign: Scalable Schema Linking for Real-World Large-Scale Multi-Database Text-to-SQLcited by 26
  5. 2024MAG-SQL: Multi-Agent Generative Approach with Soft Schema Linking and Iterative Sub-SQL Refinement for Text-to-SQLcited by 22
  6. 2025SQL-o1: A Self-Reward Heuristic Dynamic Search Method for Text-to-SQLcited by 19
  7. 2024MSc-SQL: Multi-Sample Critiquing Small Language Models For Text-To-SQL Translationcited by 17
  8. 2025BIRD-INTERACT: Re-imagining Text-to-SQL Evaluation for Large Language Models via Lens of Dynamic Interactionscited by 17
  9. 2025CSC-SQL: Corrective Self-Consistency in Text-to-SQL via Reinforcement Learningcited by 15
  10. 2025SHARE: An SLM-based Hierarchical Action CorREction Assistant for Text-to-SQLcited by 15
  11. 2025AutoLink: Autonomous Schema Exploration and Expansion for Scalable Schema Linking in Text-to-SQL at Scalecited by 15
  12. 2025Understanding, Detecting, and Repairing Real-World In-Context-Learning-Based Text-to-SQL Errorscited by 14
  13. 2026AgentSM: Semantic Memory for Agentic Text-to-SQLcited by 14
  14. 2024ROUTE: Robust Multitask Tuning and Collaboration for Text-to-SQLcited by 13
  15. 2025SQLens: An End-to-End Framework for Error Detection and Correction in Text-to-SQLcited by 10
  16. 2025SLM-SQL: An Exploration of Small Language Models for Text-to-SQLcited by 10
  17. 2025BASE-SQL: A powerful open source Text-To-SQL baseline approachcited by 9
  18. 2025Sparks of Tabular Reasoning via Text2SQL Reinforcement Learningcited by 9
  19. 2025Knowledge Base Construction for Knowledge-Augmented Text-to-SQLcited by 9
  20. 2025ReEx-SQL: Reasoning with Execution-Aware Reinforcement Learning for Text-to-SQLcited by 8
  21. 2025Text-to-SQL as Dual-State Reasoning: Integrating Adaptive Context and Progressive Generationcited by 8
  22. 2024End-to-end Text-to-SQL Generation within an Analytics Insight Enginecited by 7
  23. 2024PTD-SQL: Partitioning and Targeted Drilling with LLMs in Text-to-SQLcited by 7
  24. 2025LearNAT: Learning NL2SQL with AST-guided Task Decomposition for Large Language Modelscited by 7
  25. 2025Graph-Reward-SQL: Execution-Free Reinforcement Learning for Text-to-SQL via Graph Matching and Stepwise Rewardcited by 7
  26. 2026APEX-SQL: Talking to the data via Agentic Exploration for Text-to-SQLcited by 7
  27. 2024DAC: Decomposed Automation Correction for Text-to-SQLcited by 6
  28. 2024Leveraging Prior Experience: An Expandable Auxiliary Knowledge Base for Text-to-SQLcited by 5
  29. 2025DB-Explore: Automated Database Exploration and Instruction Synthesis for Text-to-SQLcited by 5
  30. 2025Query and Conquer: Execution-Guided SQL Generationcited by 5
  31. 2025SPFT-SQL: Enhancing Large Language Model for Text-to-SQL Parsing by Self-Play Fine-Tuningcited by 5
  32. 2025SING-SQL: A Synthetic Data Generation Framework for In-Domain Text-to-SQL Translationcited by 5
  33. 2025MCTS-SQL: Light-Weight LLMs can Master the Text-to-SQL through Monte Carlo Tree Searchcited by 4
  34. 2025GenEdit: Compounding Operators and Continuous Improvement to Tackle Text-to-SQL in the Enterprisecited by 4
  35. 2025JOLT-SQL: Joint Loss Tuning of Text-to-SQL with Confusion-aware Noisy Schema Samplingcited by 4
  36. 2025DCG-SQL: Enhancing In-Context Learning for Text-to-SQL with Deep Contextual Schema Link Graphcited by 4
  37. 2025Exploring the Landscape of Text-to-SQL with Large Language Models: Progresses, Challenges and Opportunitiescited by 4
  38. 2025RAISE: Reasoning Agent for Interactive SQL Explorationcited by 4

50 most cited of 103 All 103 (JSON)