Repository files navigation

This repository provides a comprehensive collection of research papers, benchmarks, and open-source projects onlarge 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

📃 Pleasecite our paper if you find our survey or repository helpful!

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

• Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQL [Paper] [Code]
• A Survey on Employing Large Language Models for Text-to-SQL Tasks [Paper]
• A Survey of Text-to-SQL in the Era of LLMs: Where are We, and Where are We Going? [Paper]
• Natural Language Interfaces for Tabular Data Querying and Visualization: A Survey [Paper]
• Large Language Model Enhanced Text-to-SQL Generation: A Survey [Paper]
• A Survey on Deep Learning Approaches for Text-to-SQL [Paper]
• Natural Language Interfaces for Databases with Deep Learning [Paper]
• A Survey on Text-to-SQL Parsing: Concepts, Methods, and Future Directions [Paper]
• 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 thedatasets section below.

Method/Model	Dev EX (%)	Test EX (%)	Paper/Code	Date
Agentar-Scale-SQL	74.90	81.67	[Paper]	2025-09-25
AskData + GPT-4o	76.14	80.88	[Paper]	2025-03-11
LongData-SQL	74.32	77.53	[Proprietary]	2025-07-14
CHASE-SQL + Gemini	74.90	76.02	[Paper]	2025-04-16
JoyDataAgent-SQL	74.25	75.74	[Report] [Code]	2025-09-22
TCDataAgent-SQL	74.12	75.74	[Report]	2025-05-30
Contextual-SQL	73.50	75.63	[Report] [Code]	2025-02-27

Method/Model	Dev EX (%)	Test EX (%)	Paper/Code	Date
MiniSeek	-	91.2	[Report]	2023-11-02
DAIL-SQL + GPT-4	82.4	86.6	[Paper] [Code]	2023-08-20
DIN-SQL + GPT-4	74.2	85.3	[Paper] [Code]	2023-04-21
C3 + ChatGPT	81.8	82.3	[Paper] [Code]	2023-06-01
RESDSQL-3B + NatSQL	84.1	79.9	[Paper] [Code]	2023-02-27

Method/Model	Snow Score	Lite Score	Paper/Code	Date
AgenticData + Qwen3	-	44.5	[Paper]	2025-08-07
ReFoRCE + o3	37.11	37.84	[Paper] [Code]	2025-05-22
RSL-SQL + o3	-	33.09	[Paper] [Code]	2025-07-10
LinkAlign + DeepSeek-R1	-	33.09	[Paper] [Code]	2025-04-27
Spider-Agent + Claude-3.7-Sonnet	-	28.52	[Paper] [Code]	2025-03-16

We categorize the datasets intoOriginal Datasets andPost-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. ThePost-annotated Datasets rely on the databases fromSpider 1.0. For each original dataset, we list its characteristics, number of examples, and number of databases under the dataset title.

• 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
• 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
• 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
• 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
• KaggleDBQA | KaggleDBQA: Realistic Evaluation of Text-to-SQL Parsers [Paper] [Code] [Dataset]
  Cross-domain; #Example: 272; #DB: 8
• DuSQL | DuSQL: A Large-Scale and Pragmatic Chinese Text-to-SQL Dataset [Paper] [Dataset]
  Cross-domain, Cross-lingual; #Example: 23,797; #DB: 200
• 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
• 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
• 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
• WikiSQL | Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning [Paper] [Code] [Dataset]
  Cross-domain; #Example: 80,654; #DB: 26,521

• Dr. Spider | Dr.Spider: A Diagnostic Evaluation Benchmark towards Text-to-SQL Robustness [Paper] [Code]
  Robustness; Perturbations in DB, query and SQL
• ADVETA | Towards Robustness of Text-to-SQL Models Against Natural and Realistic Adversarial Table Perturbation [Paper] [Code] [Dataset]
  Robustness; Adversarial table perturbation
• 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
• Spider-DK | Exploring Underexplored Limitations of Cross-Domain Text-to-SQL Generalization [Paper] [Code]
  Knowledge-augmented; Adding domain knowledge
• Spider-SYN | Towards Robustness of Text-to-SQL Models against Synonym Substitution [Paper] [Code]
  Knowledge-augmented; Adding domain knowledge
• Spider-Vietnames | A Pilot Study of Text-to-SQL Semantic Parsing for Vietnamese [Paper] [Code]
  Cross-lingual; Vietnamese version of Spider
• Spider-Realistic | Structure-Grounded Pretraining for Text-to-SQL [Paper] [Dataset]
  Robustness; Removing column names in question
• CSpider | A Pilot Study for Chinese SQL Semantic Parsing [Paper] [Code]
  Cross-lingual; Chinese version of Spider
• 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 inour paper, and subsequent latest research papers will be continually updated and aligned with this taxonomy.

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

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

• SQLGlot
• DB-GPT
• DB-GPT-Hub
• Awesome-Text2SQL
• PremSQL

@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}}