A Survey on Employing Large Language Models for Text-to-SQL Tasks

Liang Shi; Zhengju Tang; Nan Zhang; Xiaotong Zhang; Zhi Yang

doi:10.1145/3737873.

A Survey on Employing Large Language Models for Text-to-SQL Tasks

Computation and Language 2025-06-04 v5

Authors: Liang Shi , Zhengju Tang , Nan Zhang , Xiaotong Zhang , Zhi Yang

View on arXiv ↗ PDF ↗ DOI ↗

Abstract

With the development of the Large Language Models (LLMs), a large range of LLM-based Text-to-SQL(Text2SQL) methods have emerged. This survey provides a comprehensive review of LLM-based Text2SQL studies. We first enumerate classic benchmarks and evaluation metrics. For the two mainstream methods, prompt engineering and finetuning, we introduce a comprehensive taxonomy and offer practical insights into each subcategory. We present an overall analysis of the above methods and various models evaluated on well-known datasets and extract some characteristics. Finally, we discuss the challenges and future directions in this field.

Keywords

text-to-sql large language model evaluation large language model

Cite

@article{arxiv.2407.15186,
  title  = {A Survey on Employing Large Language Models for Text-to-SQL Tasks},
  author = {Liang Shi and Zhengju Tang and Nan Zhang and Xiaotong Zhang and Zhi Yang},
  journal= {arXiv preprint arXiv:2407.15186},
  year   = {2025}
}

Comments

Accepted by ACM Computing Surveys (CSUR)

A Survey on Employing Large Language Models for Text-to-SQL Tasks

Abstract

Keywords

Cite

Comments

Related papers