mlsanityData to 13 Oct 2026

A Survey of Large Language Model-Based Generative AI for Text-to-SQL: Benchmarks, Applications, Use Cases, and Challenges

arXiv 2412.05208 ↗First posted 6 Dec 2024cs.AI cs.DBcited by 9

Not on the map. Why?

Abstract (arXiv)

Text-to-SQL systems facilitate smooth interaction with databases by translating natural language queries into Structured Query Language (SQL), bridging the gap between non-technical users and complex database management systems. This survey provides a comprehensive overview of the evolution of AI-driven text-to-SQL systems, highlighting their foundational components, advancements in large language model (LLM) architectures, and the critical role of datasets such as Spider, WikiSQL, and CoSQL in driving progress. We examine the applications of text-to-SQL in domains like healthcare, education, and finance, emphasizing their transformative potential for improving data accessibility. Additionally, we analyze persistent challenges, including domain generalization, query optimization, support for multi-turn conversational interactions, and the limited availability of datasets tailored for NoSQL databases and dynamic real-world scenarios. To address these challenges, we outline future research directions, such as extending text-to-SQL capabilities to support NoSQL databases, designing datasets for dynamic multi-turn interactions, and optimizing systems for real-world scalability and robustness. By surveying current advancements and identifying key gaps, this paper aims to guide the next generation of research and applications in LLM-based text-to-SQL systems.

Key facts. Cited by 9 papers in the map (data through 13 Oct 2026). Builds on 20 of its 24 references that are in the map. First posted on arXiv 6 Dec 2024.

Builds on

20 of 24 references.

References · 20

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,549
  2. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,133
  3. 2017Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learningcited by 687
  4. 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 680
  5. 2019RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parserscited by 422
  6. 2021PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Modelscited by 408
  7. 2024Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflowscited by 229
  8. 2019Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representationcited by 210
  9. 2019CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databasescited by 182
  10. 2017SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learningcited by 135
  11. 2024Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQLcited by 119
  12. 2019A Comprehensive Exploration on WikiSQL with Table-Aware Word Contextualizationcited by 88
8 more
  1. 2022RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQLcited by 85
  2. 2018TypeSQL: Knowledge-based Type-Aware Neural Text-to-SQL Generationcited by 81
  3. 2024A Survey on Employing Large Language Models for Text-to-SQL Taskscited by 67
  4. 2023EHRSQL: A Practical Text-to-SQL Benchmark for Electronic Health Recordscited by 44
  5. 2019A Pilot Study for Chinese SQL Semantic Parsingcited by 33
  6. 2019X-SQL: reinforce schema representation with contextcited by 22
  7. 2024UQE: A Query Engine for Unstructured Databasescited by 19
  8. 2023UNITE: A Unified Benchmark for Text-to-SQL Evaluationcited by 14

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2025: 6; 2026: 3.

9 papers.

  1. 2025Arctic-Text2SQL-R1: Simple Rewards, Strong Reasoning in Text-to-SQLcited by 38
  2. 2025PhysGen: Physically Grounded 3D Shape Generation for Industrial Designcited by 6
  3. 2025FinStat2SQL: A Text2SQL Pipeline for Financial Statement Analysiscited by 1
  4. 2025LitE-SQL: A Lightweight and Efficient Text-to-SQL Framework with Vector-based Schema Linking and Execution-Guided Self-Correctioncited by 1
  5. 2026CYGNET: Cypher Gate for Neural Execution Triage and Cost Containmentcited by 1
  6. 2025Lightweight Transformers for Zero-Shot and Fine-Tuned Text-to-SQL Generation Using Spidercited by 0
  7. 2025Query Carefully: Detecting the Unanswerables in Text-to-SQL Taskscited by 0
  8. 2026Natural Language Interfaces for Spatial and Temporal Databases: A Comprehensive Overview of Methods, Taxonomy, and Future Directionscited by 0
  9. 2026SAFAARI: Schema-Aware Framework for Accelerated Advertiser Response Intelligencecited by 0