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

TL;DR

This survey reviews the evolution, applications, and challenges of large language model-based text-to-SQL systems, emphasizing datasets, domain applications, and future research directions for improving scalability and versatility.

Contribution

It provides a comprehensive overview of LLM-based text-to-SQL systems, highlighting recent advancements, identifying key challenges, and proposing future research directions.

Findings

LLMs have significantly advanced text-to-SQL performance.

Datasets like Spider, WikiSQL, and CoSQL are crucial for progress.

Challenges include domain generalization and multi-turn interaction support.

Abstract

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.