This repository provides a comprehensive collection of research papers, benchmarks, and open-source projects on large language model-based text-to-SQL (LLM-based Text-to-SQL). It includes all the contents from our survey paper 📖"Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQL" and will be continuously updated to incorporate the up-to-date advances and notable contributions from the text-to-SQL community. Stay tuned!!

🤗 You are vey welcome to contribute to this repository by launching an issue or a pull request. If you find any missing resources or come across interesting new research works, please don’t hesitate to open an issue or submit a PR!

📫 Contact us via emails: zijin[dot]hong[at]connect[dot]polyu[dot]hk

📃 Please cite our paper if you find our survey or repository helpful!

• [2025年10月21日] 🎉🎉 Our paper "Knapsack Optimization-based Schema Linking for LLM-based Text-to-SQL Generation" has been accepted by IEEE International Conference on Data Engineering (ICDE)!
• [2025年09月21日] 🔥🔥 Finished building the benchmarks, datasets, and taxonomy for this repository.
• [2025年09月14日] 🔥🔥 Repository launched based on our survey paper to keep track of recent progress in LLM-based text-to-SQL.
• [2025年09月02日] 🎉🎉 Our paper "Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQL" has been accepted by IEEE Transactions on Knowledge and Data Engineering (TKDE)!
• [2025年05月01日] 🎉🎉 Our paper "Struture-Guided Large Language Models for Text-to-SQL Generation" has been accepted by International Conference of Machine Learning (ICML)!

Awesome-LLM-based-Text2SQL

• 🔥 News
• 📜 Catalog
• 📈 Trends
• 📰 Surveys
• 🏆 Benchmarks
• 🗃️ Datasets
  • Original Datasets
  • Post-annotated Datasets
• 🪴 Taxonomy
  • In-cotext Learning
  • Fine-tuning
• 📦 Projects
• 📃 Citation

• TKDE Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQL [Paper] [Code]
• CSUR2025 A Survey on Employing Large Language Models for Text-to-SQL Tasks [Paper]
• TKDE A Survey of Text-to-SQL in the Era of LLMs: Where are We, and Where are We Going? [Paper]
• TKDE Natural Language Interfaces for Tabular Data Querying and Visualization: A Survey [Paper]
• arXiv2024 Large Language Model Enhanced Text-to-SQL Generation: A Survey [Paper]
• VLDBJ2023 A Survey on Deep Learning Approaches for Text-to-SQL [Paper]
• VLDB2023 Natural Language Interfaces for Databases with Deep Learning [Paper]
• arXiv2022 A Survey on Text-to-SQL Parsing: Concepts, Methods, and Future Directions [Paper]
• COLING2022 Recent Advances in Text-to-SQL: A Survey of What We Have and What We Expect [Paper]

In the era of LLMs, two benchmarks and their variants/extensions are widely recognized for evaluating text-to-SQL capabilities. We will continually update the top five methods on each benchmark to showcase the latest advances in the text-to-SQL community. These benchmarks, along with other text-to-SQL dataset papers, are listed in the datasets section below.

We categorize the datasets into Original Datasets and Post-annotated Datasets based on whether they were released with the original dataset (question–SQL pairs) and databases, or were developed by adapting existing datasets and databases with special settings. The Post-annotated Datasets rely on the databases from Spider 1.0. For each original dataset, we list its characteristics, number of examples, and number of databases under the dataset title.

• arXiv2025 BIRD-CRITIC | SWE-SQL: Illuminating LLM Pathways to Solve User SQL Issues in Real-World Applications [Paper] [Code] [Dataset]
  Knowledge-augmented, Long-context; #Example: 600; #DB: 95
• ICLR2025 Spider2.0 | Spider 2.0: Evaluating Language Models on Real-world Enterprise Text-to-SQL Workflows [Paper] [Code] [Dataset]
  Knowledge-augmented, Long-context; #Example: 632; #DB: 213
• SIGMOD2025 BULL | FinSQL: Model-Agnostic LLMs-based Text-to-SQL Framework for Financial Analysis [Paper] [Code] [Dataset]
  Knowledge-augmented, Long-context; #Example: 4,966; #DB: 3
• NeurIPS2023 BIRD | Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs [Paper] [Code] [Dataset]
  Cross-domain, Knowledge-augmented; #Example: 12,751; #DB: 95
• ACL2021 KaggleDBQA | KaggleDBQA: Realistic Evaluation of Text-to-SQL Parsers [Paper] [Code] [Dataset]
  Cross-domain; #Example: 272; #DB: 8
• EMNLP2020 DuSQL | DuSQL: A Large-Scale and Pragmatic Chinese Text-to-SQL Dataset [Paper] [Dataset]
  Cross-domain, Cross-lingual; #Example: 23,797; #DB: 200
• Findings2020 SQUALL | On the Potential of Lexico-logical Alignments for Semantic Parsing to SQL Queries [Paper] [Code]
  Cross-domain, Cross-lingual; #Example: 11,468; #DB: 1,679
• EMNLP2019 CoSQL | CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databases [Paper] [Code] [Dataset]
  Cross-domain, Context-dependent; #Example: 15,598; #DB: 200
• EMNLP2018 Spider | Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task [Paper] [Code] [Dataset]
  Cross-domain; #Example: 10,181; #DB: 200
• arXiv2017 WikiSQL | Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning [Paper] [Code] [Dataset]
  Cross-domain; #Example: 80,654; #DB: 26,521

• ICLR2023 Dr. Spider | Dr.Spider: A Diagnostic Evaluation Benchmark towards Text-to-SQL Robustness [Paper] [Code]
  Robustness; Perturbations in DB, query and SQL
• ACL2022 ADVETA | Towards Robustness of Text-to-SQL Models Against Natural and Realistic Adversarial Table Perturbation [Paper] [Code] [Dataset]
  Robustness; Adversarial table perturbation
• Findings2022 Spider-SS&CG | Measuring and Improving Compositional Generalization in Text-to-SQL via Component Alignment [Paper] [Code] [Dataset]
  Context-dependent; Splitting example into sub-examples
• EMNLP2021 Spider-DK | Exploring Underexplored Limitations of Cross-Domain Text-to-SQL Generalization [Paper] [Code]
  Knowledge-augmented; Adding domain knowledge
• ACL2021 Spider-SYN | Towards Robustness of Text-to-SQL Models against Synonym Substitution [Paper] [Code]
  Knowledge-augmented; Adding domain knowledge
• Findings2020 Spider-Vietnames | A Pilot Study of Text-to-SQL Semantic Parsing for Vietnamese [Paper] [Code]
  Cross-lingual; Vietnamese version of Spider
• NAACL2021 Spider-Realistic | Structure-Grounded Pretraining for Text-to-SQL [Paper] [Dataset]
  Robustness; Removing column names in question
• EMNLP2019 CSpider | A Pilot Study for Chinese SQL Semantic Parsing [Paper] [Code]
  Cross-lingual; Chinese version of Spider
• EMNLP2019 SParC | SParC: Cross-Domain Semantic Parsing in Context [Paper] [Code] [Dataset]
  Context-dependent; Annotate conversational contents

The implementation of recent LLM-based text-to-SQL methods primarily relies on in-context learning and fine-tuning, enabled by the release of both powerful proprietary and well-architected open-source LLMs. A detailed categorization of text-to-SQL methods can be found in our paper, and subsequent latest research papers will be continually updated and aligned with this taxonomy.

• EMNLP2025 LinkAlign: Scalable Schema Linking for Real-World Large-Scale Multi-Database Text-to-SQL [Paper] [Code]
• ICLR2025 ReFoRCE: A Text-to-SQL Agent with Self-Refinement, Consensus Enforcement, and Column Exploration [Paper] [Code]
• arXiv2025 CSC-SQL: Corrective Self-Consistency in Text-to-SQL via Reinforcement Learning [Paper] [Code]
• arXiv2025 SAFE-SQL: Self-Augmented In-Context Learning with Fine-grained Example Selection for Text-to-SQL [Paper]
• COLING2025 Gen-SQL: Efficient Text-to-SQL by Bridging Natural Language Question and Database Schema with Pseudo-Schema [Paper] [Code]
• COLING2025 In-Context Reinforcement Learning based Retrieval-Augmented Generation for Text-to-SQL [Paper]
• ICLR2025 Spider 2.0: Evaluating Language Models on Real-world Enterprise Text-to-SQL Workflows [Paper] [Code]
• arXiv2024 RSL-SQL: Robust Schema Linking in Text-to-SQL Generation [Paper] [Code]
• ICLR2025 CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQL [Paper]
• arXiv2024 E-SQL: Direct Schema Linking via Question Enrichment in Text-to-SQL [Paper] [Code]
• NeurIPS202 The Death of Schema Linking? Text-to-SQL in the Age of Well-Reasoned Language Models [Paper]
• VLDB2024 The Dawn of Natural Language to SQL: Are We Fully Ready? [Paper]
• arXiv2024 CHESS: Contextual Harnessing for Efficient SQL Synthesis [Paper] [Code]
• COLING2025 MCS-SQL: Leveraging Multiple Prompts and Multiple-Choice Selection For Text-to-SQL Generation [Paper]
• Findings2020 Before Generation, Align it! A Novel and Effective Strategy for Mitigating Hallucinations in Text-to-SQL Generation [Paper] [Code]
• arXiv2024 Dubo-SQL: Diverse Retrieval-Augmented Generation and Fine Tuning for Text-to-SQL [Paper] [Code]
• AAAI2025 MAGIC: Generating Self-Correction Guideline for In-Context Text-to-SQL [Paper] [Code]
• NAACL2025 You Only Read Once (YORO): Learning to Internalize Database Knowledge for Text-to-SQL [Paper]
• ICDE2024 PURPLE: Making a Large Language Model a Better SQL Writer [Paper]
• arXiv2024 PET-SQL: A Prompt-Enhanced Two-Round Refinement of Text-to-SQL with Cross-consistency [Paper] [Code]
• ACL2025 R3: "This is My SQL, Are You With Me?" A Consensus-Based Multi-Agent System for Text-to-SQL Tasks [Paper] [Code]
• ICDE2024 MetaSQL: A Generate-then-Rank Framework for Natural Language to SQL Translation [Paper] [Code]
• EMNLP2024 Middleware for LLMs: Tools Are Instrumental for Language Agents in Complex Environments [Paper] [Code]
• arXiv2024 SQL-CRAFT: Text-to-SQL through Interactive Refinement and Enhanced Reasoning [Paper]
• ICML2025 Structure-Guided Large Language Models for Text-to-SQL Generation [Paper]
• Findings2020 Knowledge-to-SQL: Enhancing SQL Generation with Data Expert LLM [Paper] [Code]
• Findings2024 Improving Demonstration Diversity by Human-Free Fusing for Text-to-SQL [Paper] [Code]
• Findings2020 Decomposition for Enhancing Attention: Improving LLM-based Text-to-SQL through Workflow Paradigm [Paper] [Code]
• COLING2025 MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQL [Paper] [Code]
• Findings2023 ACT-SQL: In-Context Learning for Text-to-SQL with Automatically-Generated Chain-of-Thought [Paper] [Code]
• Findings2023 Selective Demonstrations for Cross-domain Text-to-SQL [Paper] [Code]
• VLDB2024 Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation [Paper] [Code]
• arXiv2023 C3: Zero-shot Text-to-SQL with ChatGPT [Paper] [Code]
• ICONIP2023 Retrieval-augmented GPT-3.5-based Text-to-SQL Framework with Sample-aware Prompting and Dynamic Revision Chain [Paper]
• TMLR2024 SQL-PaLM: Improved Large Language Model Adaptation for Text-to-SQL [Paper]
• EMNLP2023 Exploring Chain of Thought Style Prompting for Text-to-SQL [Paper]
• Findings2023 Enhancing Text-to-SQL Capabilities of Large Language Models: A Study on Prompt Design Strategies [Paper]
• EMNLP2023 StructGPT: A General Framework for Large Language Model to Reason over Structured Data [Paper] [Code]
• NeurIPS2023 DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction [Paper] [Code]
• PRICAI2023 Prompting GPT-3.5 for Text-to-SQL with De-semanticization and Skeleton Retrieval [Paper]
• ICLR2024 Teaching Large Language Models to Self-Debug [Paper]
• ICML2023 LEVER: Learning to Verify Language-to-Code Generation with Execution [Paper] [Code]
• ICML2023 Coder Reviewer Reranking for Code Generation [Paper]
• EMNLP2022 Natural Language to Code Translation with Execution [Paper] [Code]

• ACL2025 SHARE: An SLM-based Hierarchical Action CorREction Assistant for Text-to-SQL [Paper] [Code]
• ICLR2025 ROUTE: Robust Multitask Tuning and Collaboration for Text-to-SQL [Paper] [Code]
• arXiv2024 A Preview of XiYan-SQL: A Multi-Generator Ensemble Framework for Text-to-SQL [Paper] [Code]
• NAACL2025 MSc-SQL: Multi-Sample Critiquing Small Language Models For Text-To-SQL Translation [Paper] [Code]
• arXiv2025 Knapsack Optimization-based Schema Linking for LLM-based Text-to-SQL Generation [Paper]
• Findings2024 DTS-SQL: Decomposed Text-to-SQL with Small Large Language Models [Paper] [Code]
• COLING2025 MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQL [Paper] [Code]
• NeurIPS202 The Death of Schema Linking? Text-to-SQL in the Age of Well-Reasoned Language Models [Paper]
• arXiv2024 Dubo-SQL: Diverse Retrieval-Augmented Generation and Fine Tuning for Text-to-SQL [Paper] [Code]
• COLM2024 StructLM: Towards Building Generalist Models for Structured Knowledge Grounding [Paper] [Code]
• SIGMOD2024 CodeS: Towards Building Open-source Language Models for Text-to-SQL [Paper] [Code]
• ACL2024 Symbol-LLM: Towards Foundational Symbol-centric Interface For Large Language Models [Paper] [Code]
• VLDB2024 Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation [Paper] [Code]
• ICML2024 CLLMs: Consistency Large Language Models [Paper] [Code]

• SQLGlot GitHub Repo stars
• DB-GPT GitHub Repo stars
• DB-GPT-Hub GitHub Repo stars
• Awesome-Text2SQL GitHub Repo stars
• PremSQL GitHub Repo stars

@article{hong2025next,
 title={Next-generation database interfaces: A survey of llm-based text-to-sql},
 author={Hong, Zijin and Yuan, Zheng and Zhang, Qinggang and Chen, Hao and Dong, Junnan and Huang, Feiran and Huang, Xiao},
 journal={IEEE Transactions on Knowledge and Data Engineering},
 year={2025}
}