NL2SQL Handbook

From this repository, you can view the latest advancements in NL2SQL. This handbook corresponds to our survey paper: A Survey of NL2SQL with Large Language Models: Where are we, and where are we going?. We also provide tutorial slides to summarize the key points of this survey. Based on the trends in the development of language models, we have created a river diagram of NL2SQL methods to trace the evolution of the NL2SQL field.

If you are a novice, don't worry—we have prepared a practical guide for you, covering a wide range of foundational materials here. We summarized NL2SQL related applications.

@article{liu2024survey,
  title={A Survey of NL2SQL with Large Language Models: Where are we, and where are we going?},
  author={Liu, Xinyu and Shen, Shuyu and Li, Boyan and Ma, Peixian and Jiang, Runzhi and Zhang, Yuxin and Fan, Ju and Li, Guoliang and Tang, Nan and Luo, Yuyu},
  journal={arXiv preprint arXiv:2408.05109},
  year={2024}
}

Translating users' natural language queries (NL) into SQL queries can significantly reduce barriers to accessing relational databases and support various commercial applications. The performance of NL2SQL has been greatly improved with the emergence of language models (LMs). In this context, it is crucial to assess our current position, determine the NL2SQL solutions that should be adopted for specific scenarios by practitioners, and identify the research topics that researchers should explore next.

• Model: NL2SQL translation techniques that tackle not only NL ambiguity and under-specification, but also properly map NL with database schema and instances;

• Data: From the collection of training data, data synthesis due to training data scarcity, to NL2SQL benchmarks;

• Evaluation: Evaluating NL2SQL methods from multiple angles using different metrics and granularities;

• Error Analysis: analyzing NL2SQL errors to find the root cause and guiding NL2SQL models to evolve.

we categorize the challenges of NL2SQL into five levels, each addressing specific hurdles. The first three levels cover challenges that have been or are currently being addressed, reflecting the progressive development of NL2SQL. The fourth level represents the challenges we aim to tackle in the LLMs stage, while the fifth level outlines our vision for NL2SQL system in the next five years.

We describe the evolution of NL2SQL solutions from the perspective of language models, categorizing it into four stages. For each stage of NL2SQL, we analyze the changes in target users and the extent to which challenges are addressed.

We summarize the key modules of NL2SQL solutions utilizing the language model.

• Pre-processing serves as an enhancement to the model’s inputs in the NL2SQL parsing process. You can get more details from this chapter: Pre-Processing
• NL2SQL translation methods constitute the core of the NL2SQL solution, responsible for converting input natural language queries into SQL queries. You can get more details from this chapter: NL2SQL Translation Methods
• Post-processing is a crucial step to refine the generated SQL queries, ensuring they meet user expectations more accurately. You can get more details from this chapter: Post-Processing

1. A Survey of NL2SQL with Large Language Models: Where are we, and where are we going？
2. Next-generation databas interfaces: A survey of llm-based text-to-sql.
3. Large Language Model Enhanced Text-to-SQL Generation: A Survey.
4. From Natural Language to SQL: Review of LLM-based Text-to-SQL Systems.
5. A Survey on Employing Large Language Models for Text-to-SQL Tasks.
6. Natural language interfaces for tabular data querying and visualization: A survey.
7. Natural Language Interfaces for Databases with Deep Learning.
8. A survey on deep learning approaches for text-to-SQL.
9. Recent Advances in Text-to-SQL: A Survey of What We Have and What We Expect.
10. A Deep Dive into Deep Learning Approaches for Text-to-SQL Systems.
11. State of the Art and Open Challenges in Natural Language Interfaces to Data.
12. Natural language to SQL: Where are we today?

1. OpenSearch-SQL: Enhancing Text-to-SQL with Dynamic Few-shot and Consistency Alignment.

2. Reliable Text-to-SQL with Adaptive Abstention.

3. SNAILS: Schema Naming Assessments for Improved LLM-Based SQL Inference.

4. CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQL.

5. Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows.

6. ROUTE: ROBUST MULTITASK TUNING AND COLLAB- ORATION FOR TEXT-TO-SQL.

7. Confidence Estimation for Error Detection in Text-to-SQL Systems.

8. DBCopilot: Scaling Natural Language Querying to Massive Databases.

9. Boosting Text-to-SOL through Multi- grained Error Identification.

10. Gen-SQL: Efficient Text-to-SQL By Bridging Natural Language Question And Database Schema With Pseudo-Schema.

11. Utilising Large Language Models for Adversarial Attacks in Text-to-SQL: A Perpetrator and Victim Approach

12. You Only Read Once (YORO): Learning to Internalize Database Knowledge for Text-to-SQL.

13. Alpha-SQL: Zero-Shot Text-to-SQL using Monte Carlo Tree Search

14. NL2SQL-BUGs: A Benchmark for Detecting Semantic Errors in NL2SQL Translation.

15. OmniSQL: Synthesizing High-quality Text-to-SQL Data at Scale.

16. Automatic database description generation for Text-to-SQL

17. Is Long Context AIl You Need? Leveraging LLM's ExtendedContext for NL2SQL.

18. MCTS-SQL: An Effective Framework for Text-to-SQL with Monte Carlo Tree Search.

19. SQL-o1: A Self-Reward Heuristic Dynamic Search Method for Text-to-SQL.

20. FEATHER-SQL: A LIGHTWEIGHT NL2SQL FRAME- WORK WITH DUAL-MODEL COLLABORATION PARADIGM FOR SMALL LANGUAGE MODELS.

21. FI-NL2PY2SQL: Financial Industry NL2SQL Innovation Model Based on Python and Large Language Model.

22. FGCSQL: A Three-Stage Pipeline for Large Language Model-Driven Chinese Text-to-SQL

23. Transforming Medical Data Access: The Role and Challenges of Recent Language Models in SQL Query Automation.

24. The Dawn of Natural Language to SQL: Are We Fully Ready?

25. Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation.

26. Interleaving Pre-Trained Language Models and Large Language Models for Zero-Shot NL2SQL Generation.

27. Generating Succinct Descriptions of Database Schemata for Cost-Efficient Prompting of Large Language Models.

28. ScienceBenchmark: A Complex Real-World Benchmark for Evaluating Natural Language to SQL Systems.

29. CodeS: Towards Building Open-source Language Models for Text-to-SQL.

30. FinSQL: Model-Agnostic LLMs-based Text-to-SQL Framework for Financial Analysis.

31. PURPLE: Making a Large Language Model a Better SQL Writer.

32. METASQL: A Generate-then-Rank Framework for Natural Language to SQL Translation.

33. Archer: A Human-Labeled Text-to-SQL Dataset with Arithmetic, Commonsense and Hypothetical Reasoning.

34. Synthesizing Text-to-SQL Data from Weak and Strong LLMs.

35. Understanding the Effects of Noise in Text-to-SQL: An Examination of the BIRD-Bench Benchmark.

36. I Need Help! Evaluating LLM’s Ability to Ask for Users’ Support: A Case Study on Text-to-SQL Generation.

37. PTD-SQL: Partitioning and Targeted Drilling with LLMs in Text-to-SQL.

38. Improving Retrieval-augmented Text-to-SQL with AST-based Ranking and Schema Pruning.

39. Data-Centric Text-to-SQL with Large Language Models.

40. Research and Practice on Database Interaction Based on Natural Language Processing

41. XiYan-SQL: A Multi-Generator Ensemble Framework for Text-to-SQL.

42. Structure Guided Large Language Model for SQL Generation.

43. A Plug-and-Play Natural Language Rewriter for Natural Language to SQL.

44. RSL-SQL: Robust Schema Linking in Text-to-SQL Generation.
    

45. In-Context Reinforcement Learning based Retrieval-Augmented Generation for Text-to-SQL.

46. TrustSQL: Benchmarking Text-to-SQL Reliability with Penalty-Based Scoring.

47. LAIA-SQL: Enhancing Natural Language to SQL Generation in Multi-Table QA via Task Decomposition and Keyword Extraction

48. Research on Large Model Text-to-SQL Optimization Method for Intelligent Interaction in the Field of Construction Safety.

49. SQLh-GEN: Bridging the Dialect Gap for Text-to-SQL Via Synthetic Data And Model Merging.

50. Grounding Natural Language to SQL Translation with Data-Based Self-Explanations.

51. Towards Optimizing SQL Generation via LLM Routing.

52. E-SQL: Direct Schema Linking via Question Enrichment in Text-to-SQL.

53. DB-GPT: Empowering Database Interactions with Private Large Language Models.

54. The Death of Schema Linking? Text-to-SQL in the Age of Well-Reasoned Language Models.

55. CHESS: Contextual Harnessing for Efficient SQL Synthesis.

56. PET-SQL: A Prompt-Enhanced Two-Round Refinement of Text-to-SQL with Cross-consistency.

57. CoE-SQL: In-Context Learning for Multi-Turn Text-to-SQL with Chain-of-Editions.

58. AMBROSIA: A Benchmark for Parsing Ambiguous Questions into Database Queries.

59. Text-to-SQL Calibration: No Need to Ask—Just Rescale Model Probabilities.

60. Few-shot Text-to-SQL Translation using Structure and Content Prompt Learning.

61. CatSQL: Towards Real World Natural Language to SQL Applications.

62. DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction.

63. Data Ambiguity Strikes Back: How Documentation Improves GPT's Text-to-SQL.

64. ACT-SQL: In-Context Learning for Text-to-SQL with Automatically-Generated Chain-of-Thought.

65. Selective Demonstrations for Cross-domain Text-to-SQL.

66. RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQL.

67. Graphix-T5: Mixing Pre-trained Transformers with Graph-Aware Layers for Text-to-SQL Parsing.

68. Improving Generalization in Language Model-based Text-to-SQL Semantic Parsing: Two Simple Semantic Boundary-based Techniques.

69. G³R: A Graph-Guided Generate-and-Rerank Framework for Complex and Cross-domain Text-to-SQL Generation.

70. Importance of Synthesizing High-quality Data for Text-to-SQL Parsing.

71. Know What I don’t Know: Handling Ambiguous and Unknown Questions for Text-to-SQL.

72. C3: Zero-shot Text-to-SQL with ChatGPT

73. MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQL.

74. SQLformer: Deep Auto-Regressive Query Graph Generation for Text-to-SQL Translation.

We create a timeline of the benchmark's development and mark relevant milestones. You can get more details from this chapter: 📊 Benchmark

• 🎯Sovle Open NL2SQL Problem
• 🎯Develop Cost-effective NL2SQL Methods
• 🎯Make NL2SQL Solutions Trustworthy
• 🎯NL2SQL with Ambiguous and Unspecified NL Queries
• 🎯Adaptive Training Data Synthesis

You can get more information from our subsection. We introduce representative papers on related concepts:

• Pre-Processing
• NL2SQL Translation Methods
• Post-Processing
• Benchmark
• Evaluation
• Error Analysis

• We collect NL2SQL benchmark features and download links for you. You can get more details from this chapter: Benchmark
• The analysis code for benchmarks is available in the src/dataset_analysis directory. Benchmark analysis reports can be found in the report/ directory.

• Litgpt Repository Link

  This repository offers access to over 20 high-performance large language models (LLMs) with comprehensive guides for pretraining, fine-tuning, and deploying at scale. It is designed to be beginner-friendly with from-scratch implementations and no complex abstractions.

• LLaMA-Factory Repository Link Unified Efficient Fine-Tuning of 100+ LLMs. Integrating various models with scalable training resources, advanced algorithms, practical tricks, and comprehensive experiment monitoring tools, this setup enables efficient and faster inference through optimized APIs and UIs.

• Fine-tuning and In-Context learning for BIRD-SQL benchmark Repository Link

  A tutorial for both Fine-tuning and In-Context Learning is provided by the BIRD-SQL benchmark.

We collect NL2SQL evaluation metrics for you. You can get more details from this chapter: Evaluation

• NLSQL360 Repository Link

  NL2SQL360 is a testbed for fine-grained evaluation of NL2SQL solutions. Our testbed integrates existing NL2SQL benchmarks, a repository of NL2SQL models, and various evaluation metrics, which aims to provide an intuitive and user-friendly platform to enable both standard and customized performance evaluations.

• Test-suite-sql-eval Repository Link

  This repo contains a test suite evaluation metric for 11 text-to-SQL tasks. It is now the official metric of Spider, SParC, and CoSQL, and is also now available for Academic, ATIS, Advising, Geography, IMDB, Restaurants, Scholar, and Yelp (building on the amazing work by Catherine and Jonathan).

• BIRD-SQL-Official Repository Link

  It is now the official tool of BIRD-SQL. It is the first tool to propose VES and give an official test suite.

You can get some inspiration from the Roadmap and Decision Flow.

• Chat2DB: AI-driven database tool and SQL client, The hottest GUI client, supporting MySQL, Oracle, PostgreSQL, DB2, SQL Server, DB2, SQLite, H2, ClickHouse, and more.
• DB-GPT: AI Native Data App Development framework with AWEL(Agentic Workflow Expression Language) and Agents.
• Postgres.new: In-browser Postgres sandbox with AI assistance.