# Large Language Model Enhanced Text-to-SQL Generation: A Survey

arXiv: https://arxiv.org/abs/2410.06011 · HTML: https://mlsanity.com/paper/2410.06011/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Oct 2024.

## Built on by (most cited first, 24 of 24)

- [Arctic-Text2SQL-R1: Simple Rewards, Strong Reasoning in Text-to-SQL](https://mlsanity.com/paper/2505.20315/) (2025)
- [LLM/Agent-as-Data-Analyst: A Survey](https://mlsanity.com/paper/2509.23988/) (2025)
- [Fundamentals of Building Autonomous LLM Agents](https://mlsanity.com/paper/2510.09244/) (2025)
- [Role-Conditioned Refusals: Evaluating Access Control Reasoning in Large Language Models](https://mlsanity.com/paper/2510.07642/) (2025)
- [Rethinking Supply Chain Planning: A Generative Paradigm](https://mlsanity.com/paper/2509.03811/) (2025)
- [Rethinking Schema Linking: A Context-Aware Bidirectional Retrieval Approach for Text-to-SQL](https://mlsanity.com/paper/2510.14296/) (2025)
- [SchemaGraphSQL: Efficient Schema Linking with Pathfinding Graph Algorithms for Text-to-SQL on Large-Scale Databases](https://mlsanity.com/paper/2505.18363/) (2025)
- [Distill-C: Enhanced NL2SQL via Distilled Customization with LLMs](https://mlsanity.com/paper/2504.00048/) (2025)
- [HES-SQL: Hybrid Reasoning for Efficient Text-to-SQL with Structural Skeleton Guidance](https://mlsanity.com/paper/2510.08896/) (2025)
- [Software-Defined Agentic Serving](https://mlsanity.com/paper/2601.03197/) (2026)
- [Both Ends Count! Just How Good are LLM Agents at "Text-to-Big SQL"?](https://mlsanity.com/paper/2602.21480/) (2026)
- [NL2SQLBench: A Modular Benchmarking Framework for LLM-Enabled NL2SQL Solutions](https://mlsanity.com/paper/2604.16493/) (2026)
- [SQLCritic: Correcting Text-to-SQL Generation via Clause-wise Critic](https://mlsanity.com/paper/2503.07996/) (2025)
- [Design and testing of an agent chatbot supporting decision making with public transport data](https://mlsanity.com/paper/2505.22698/) (2025)
- [SPOT: Bridging Natural Language and Geospatial Search for Investigative Journalists](https://mlsanity.com/paper/2506.13188/) (2025)
- [VizGen: Data Exploration and Visualization from Natural Language via a Multi-Agent AI Architecture](https://mlsanity.com/paper/2509.22218/) (2025)
- [FinAI Data Assistant: LLM-based Financial Database Query Processing with the OpenAI Function Calling API](https://mlsanity.com/paper/2510.14162/) (2025)
- [BAPPA: Benchmarking Agents, Plans, and Pipelines for Automated Text-to-SQL Generation](https://mlsanity.com/paper/2511.04153/) (2025)
- [AskDB: An LLM Agent for Natural Language Interaction with Relational Databases](https://mlsanity.com/paper/2511.16131/) (2025)
- [SCARE: A Benchmark for SQL Correction and Question Answerability Classification for Reliable EHR Question Answering](https://mlsanity.com/paper/2511.17559/) (2025)
- [RingSQL: Schema-Independent Synthetic Data Generation for Text-to-SQL Reinforcement Learning](https://mlsanity.com/paper/2601.05451/) (2026)
- [An Agentic System for Schema Aware NL2SQL Generation](https://mlsanity.com/paper/2603.18018/) (2026)
- [Natural Language Interfaces for Spatial and Temporal Databases: A Comprehensive Overview of Methods, Taxonomy, and Future Directions](https://mlsanity.com/paper/2603.23375/) (2026)
- [KGVoyager: Knowledge Graph Agnostic Question Answering via Agentic Navigation](https://mlsanity.com/paper/2609.01780/) (2026)

## Abstract (arXiv)

Text-to-SQL translates natural language queries into Structured Query Language (SQL) commands, enabling users to interact with databases using natural language. Essentially, the text-to-SQL task is a text generation task, and its development is primarily dependent on changes in language models. Especially with the rapid development of Large Language Models (LLMs), the pattern of text-to-SQL has undergone significant changes. Existing survey work mainly focuses on rule-based and neural-based approaches, but it still lacks a survey of Text-to-SQL with LLMs. In this paper, we survey the large language model enhanced text-to-SQL generations, classifying them into prompt engineering, fine-tuning, pre-trained, and Agent groups according to training strategies. We also summarize datasets and evaluation metrics comprehensively. This survey could help people better understand the pattern, research status, and challenges of LLM-based text-to-SQL generations.