mlsanityData to 14 Oct 2026

A Survey on Employing Large Language Models for Text-to-SQL Tasks

arXiv 2407.15186 ↗First posted 21 Jul 2024cs.CLcited by 67

Not on the map. Why?

Abstract (arXiv)

With the development of the Large Language Models (LLMs), a large range of LLM-based Text-to-SQL(Text2SQL) methods have emerged. This survey provides a comprehensive review of LLM-based Text2SQL studies. We first enumerate classic benchmarks and evaluation metrics. For the two mainstream methods, prompt engineering and finetuning, we introduce a comprehensive taxonomy and offer practical insights into each subcategory. We present an overall analysis of the above methods and various models evaluated on well-known datasets and extract some characteristics. Finally, we discuss the challenges and future directions in this field.

Key facts. Cited by 67 papers in the map (data through 14 Oct 2026). Builds on 108 of its 162 references that are in the map. First posted on arXiv 21 Jul 2024.

Builds on

108 of 162 references.

References · 108

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2020Language Models are Few-Shot Learnerscited by 32,419
  4. 2023GPT-4 Technical Reportcited by 18,396
  5. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  6. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  7. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  8. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  9. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  10. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  11. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  12. 2020Scaling Laws for Neural Language Modelscited by 6,586
38 more
  1. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  2. 2021Prefix-Tuning: Optimizing Continuous Prompts for Generationcited by 3,915
  3. 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,795
  4. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,780
  5. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,720
  6. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,418
  7. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
  8. 2014Sequence to Sequence Learning with Neural Networkscited by 2,986
  9. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,724
  10. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,242
  11. 2023Code Llama: Open Foundation Models for Codecited by 2,139
  12. 2024DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligencecited by 1,181
  13. 2023PaLM 2 Technical Reportcited by 1,162
  14. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,139
  15. 2023Teaching Large Language Models to Self-Debugcited by 988
  16. 2022Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learningcited by 896
  17. 2022CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesiscited by 885
  18. 2023StarCoder: may the source be with you!cited by 799
  19. 2023Can Large Language Models Be an Alternative to Human Evaluations?cited by 734
  20. 2021P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Taskscited by 689
  21. 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 688
  22. 2017Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learningcited by 687
  23. 2024Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Surveycited by 656
  24. 2022Decomposed Prompting: A Modular Approach for Solving Complex Taskscited by 558
  25. 2022InCoder: A Generative Model for Code Infilling and Synthesiscited by 498
  26. 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 477
  27. 2019TabFact: A Large-scale Dataset for Table-based Fact Verificationcited by 428
  28. 2019RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parserscited by 424
  29. 2021PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Modelscited by 411
  30. 2022Unnatural Instructions: Tuning Language Models with (Almost) No Human Laborcited by 397
  31. 2023Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluationcited by 385
  32. 2024Break the Sequential Dependency of LLM Inference Using Lookahead Decodingcited by 298
  33. 2023LEVER: Learning to Verify Language-to-Code Generation with Executioncited by 239
  34. 2023Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategiescited by 238
  35. 2022Binding Language Models in Symbolic Languagescited by 228
  36. 2023How Abilities in Large Language Models are Affected by Supervised Fine-tuning Data Compositioncited by 223
  37. 2023RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQLcited by 195
  38. 2024CodeS: Towards Building Open-source Language Models for Text-to-SQLcited by 187

50 most cited of 108 All 108 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 7; 2025: 36; 2026: 24.

67 papers.

Sort:

By area:

  1. 2024A Survey of Text-to-SQL in the Era of LLMs: Where are we, and where are we going?cited by 56
  2. 2025In-Context Learning Is Provably Bayesian Inference: A Generalization Theory for Meta-Learningcited by 22
  3. 2025BIRD-INTERACT: Re-imagining Text-to-SQL Evaluation for Large Language Models via Lens of Dynamic Interactionscited by 19
  4. 2025AutoLink: Autonomous Schema Exploration and Expansion for Scalable Schema Linking in Text-to-SQL at Scalecited by 17
  5. 2025LLM/Agent-as-Data-Analyst: A Surveycited by 16
  6. 2025CSC-SQL: Corrective Self-Consistency in Text-to-SQL via Reinforcement Learningcited by 15
  7. 2024FLEX: Expert-level False-Less EXecution Metric for Reliable Text-to-SQL Benchmarkcited by 11
  8. 2025SQLForge: Synthesizing Reliable and Diverse Data to Enhance Text-to-SQL Reasoning in LLMscited by 11
  9. 2024A Survey of Large Language Model-Based Generative AI for Text-to-SQL: Benchmarks, Applications, Use Cases, and Challengescited by 10
  10. 2024Auto-Cypher: Improving LLMs on Cypher generation via LLM-supervised generation-verification frameworkcited by 10
  11. 2025SLM-SQL: An Exploration of Small Language Models for Text-to-SQLcited by 10
  12. 2025BASE-SQL: A powerful open source Text-To-SQL baseline approachcited by 9
38 more
  1. 2026APEX-SQL: Talking to the data via Agentic Exploration for Text-to-SQLcited by 8
  2. 2025Mixture-of-Minds: Multi-Agent Reinforcement Learning for Table Understandingcited by 7
  3. 2024DAC: Decomposed Automation Correction for Text-to-SQLcited by 6
  4. 2025SQL-of-Thought: Multi-agentic Text-to-SQL with Guided Error Correctioncited by 6
  5. 2024Towards Action Hijacking of Large Language Model-based Agentcited by 4
  6. 2025MCTS-SQL: Light-Weight LLMs can Master the Text-to-SQL through Monte Carlo Tree Searchcited by 4
  7. 2025JOLT-SQL: Joint Loss Tuning of Text-to-SQL with Confusion-aware Noisy Schema Samplingcited by 4
  8. 2025SEED: Enhancing Text-to-SQL Performance and Practical Usability Through Automatic Evidence Generationcited by 4
  9. 2025SpotIt: Evaluating Text-to-SQL Evaluation with Formal Verificationcited by 4
  10. 2025RulePilot: An LLM-Powered Agent for Security Rule Generationcited by 4
  11. 2025LLM and Agent-Driven Data Analysis: A Systematic Approach for Enterprise Applications and System-level Deploymentcited by 4
  12. 2025MaskSQL: Safeguarding Privacy for LLM-Based Text-to-SQL via Abstractioncited by 3
  13. 2025Chatty-KG: A Multi-Agent AI System for On-Demand Conversational Question Answering over Knowledge Graphscited by 3
  14. 2026Semantic Layers for Reliable LLM-Powered Data Analytics: A Paired Benchmark of Accuracy and Hallucination Across Three Frontier Modelscited by 3
  15. 2025Balancing Content Size in RAG-Text2SQL Systemcited by 2
  16. 2025RetrySQL: text-to-SQL training with retry data for self-correcting query generationcited by 2
  17. 2025STARQA: A Question Answering Dataset for Complex Analytical Reasoning over Structured Databasescited by 2
  18. 2025GeoSQL-Eval: First Evaluation of LLMs on PostGIS-Based NL2GeoSQL Queriescited by 2
  19. 2026CLARITY: A Framework and Benchmark for Conversational Language Ambiguity and Unanswerability in Interactive NL2SQL Systemscited by 2
  20. 2025Schema-R1: A reasoning training approach for schema linking in Text-to-SQL Taskcited by 1
  21. 2025Agentic NL2SQL to Reduce Computational Costscited by 1
  22. 2025Squrve: A Unified and Modular Framework for Complex Real-World Text-to-SQL Taskscited by 1
  23. 2025From Natural Language to Control Signals: A Conceptual Framework for Semantic Channel Finding in Complex Experimental Infrastructurecited by 1
  24. 2026Beyond Static Pipelines: Learning Dynamic Workflows for Text-to-SQLcited by 1
  25. 2026Evaluation of LLMs in retrieving food and nutritional context for RAG systemscited by 1
  26. 2026NL2SQLBench: A Modular Benchmarking Framework for LLM-Enabled NL2SQL Solutionscited by 1
  27. 2026CYGNET: Cypher Gate for Neural Execution Triage and Cost Containmentcited by 1
  28. 2026EXPO-SQL: Execution-based Clause-level Policy Optimization for Text-to-SQLcited by 1
  29. 2024LR-SQL: A Supervised Fine-Tuning Method for Text2SQL Tasks under Low-Resource Scenarioscited by 0
  30. 2025Investigating the (De)Composition Capabilities of Large Language Models in Natural-to-Formal Language Conversioncited by 0
  31. 2025Exploring Generative AI Techniques in Government: A Case Studycited by 0
  32. 2025UNJOIN: Enhancing Multi-Table Text-to-SQL Generation via Schema Simplificationcited by 0
  33. 2025Meta-aware Learning in text-to-SQL Large Language Modelcited by 0
  34. 2025SPOT: Bridging Natural Language and Geospatial Search for Investigative Journalistscited by 0
  35. 2025HI-SQL: Optimizing Text-to-SQL Systems through Dynamic Hint Integrationcited by 0
  36. 2025Bootstrapping Learned Cost Models with Synthetic SQL Queriescited by 0
  37. 2025FinAI Data Assistant: LLM-based Financial Database Query Processing with the OpenAI Function Calling APIcited by 0
  38. 2025AskDB: An LLM Agent for Natural Language Interaction with Relational Databasescited by 0

50 most cited of 67 All 67 (JSON)