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

2024-12-06

arXiv.org

AI Summary

Non-technical users face significant barriers in directly querying databases, necessitating robust Text-to-SQL systems. Method: This paper systematically surveys recent advances in large language model (LLM)-driven Text-to-SQL, evaluating performance on canonical benchmarks—Spider, WikiSQL, and CoSQL—and analyzing cross-domain applications in healthcare, finance, and education. Contribution/Results: We identify four critical bottlenecks: weak domain generalization, inadequate support for multi-turn dialogue, poor NoSQL compatibility, and low robustness in real-world deployments. Innovatively, we (1) establish the first coherent evolutionary framework for Text-to-SQL in the LLM era; (2) propose a dynamic paradigm for constructing multi-turn interactive training data; and (3) pinpoint NoSQL adaptation and industrial-scale scalability optimization as pivotal research directions. Collectively, this work provides a theoretical foundation and actionable roadmap for transitioning Text-to-SQL from academic prototypes to production-ready, adaptive, and robust database interfaces.

Technology Category

• Natural Language Processing: Question Answering
• Machine Learning: Large Multimodal Models (LMMs)
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Large language models for search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

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.

Problem

• AI-driven SQL query generation
• Non-technical user database interaction
• NoSQL database compatibility

Innovation

• Large Language Models
• Natural Language to SQL
• Advanced AI