Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Xiaohu Zhu, Qian Li, Lizhen Cui, Yongkang Liu

TL;DR

The paper surveys the emergence of large language model–driven Text-to-SQL generation, organizing approaches into prompt engineering, fine-tuning, task-training, and agent paradigms. It highlights how LLMs, combined with structured prompts, pretraining, and external tools, advance SQL generation across single- and cross-domain databases, while detailing evaluation metrics and diverse datasets. Key contributions include a taxonomy of methods, synthesis of datasets and benchmarks, and discussion of challenges such as schema linking, robustness, and efficiency. The work clarifies practical implications for deploying LLM-based Text-to-SQL systems in real-world, enterprise-like environments and identifies avenues for future research toward smarter, scalable, and generalizable SQL generation.

Abstract

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.

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

TL;DR

The paper surveys the emergence of large language model–driven Text-to-SQL generation, organizing approaches into prompt engineering, fine-tuning, task-training, and agent paradigms. It highlights how LLMs, combined with structured prompts, pretraining, and external tools, advance SQL generation across single- and cross-domain databases, while detailing evaluation metrics and diverse datasets. Key contributions include a taxonomy of methods, synthesis of datasets and benchmarks, and discussion of challenges such as schema linking, robustness, and efficiency. The work clarifies practical implications for deploying LLM-based Text-to-SQL systems in real-world, enterprise-like environments and identifies avenues for future research toward smarter, scalable, and generalizable SQL generation.

Abstract

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.
Paper Structure (36 sections, 5 equations, 3 figures, 2 tables)

This paper contains 36 sections, 5 equations, 3 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Preliminaries
  3. The Text-to-SQL problem
  4. Mythology
  5. Challenges
  6. Word Segmentation and Sense Ambiguity
  7. Database size and diversity
  8. Complexity of SQL queries
  9. Pragmatic Ambiguity
  10. Robustness and Efficiency
  11. Metrics and Datasets
  12. Evaluation Metric
  13. Exact Matching Accuracy(EM)
  14. Execution Accuracy(EX)
  15. Valid Efficiency Score
  16. ...and 21 more sections

Figures (3)

  • Figure 1: Flowchart of the Text-to-SQL. The flowchart illustrates the process where user questions and the database schema are first collected. These inputs are then processed through prompt engineering and fine-tuning techniques before being passed to a large language model (LLM). The LLM generates the corresponding SQL query based on the refined inputs, allowing for accurate query formulation based on natural language input.
  • Figure 2: The overview of the text-to-SQL metrics, datasets, and methods.
  • Figure 3: Prompt Engineering Methods. The figure illustrates three key prompt engineering approaches for Text-to-SQL: (a) zero-shot, where the model generates SQL without prior examples; (b) few-shot, which provides a few examples to guide query generation; (c) Reasoning, breaking down the reasoning process step-by-step for complex queries.