Next-Generation Database Interfaces: A Survey of LLM-based Text-to-SQL

2024/06/12 by Zijin Hong, Zheng Yuan, Hong, Zijin +11 · 43 citations
Computer Science · #Advanced Computational Techniques and Applications #Advanced Database Systems and Queries #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Databases (cs.DB) #FOS: Computer and information sciences

paper · pdf · doi:10.48550/arxiv.2406.08426

openalex publication_date 2024/06/12 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Generating accurate SQL from users' natural language questions (text-to-SQL) remains a long-standing challenge due to the complexities involved in user question understanding, database schema comprehension, and SQL generation. Traditional text-to-SQL systems, which combine human engineering and deep neural networks, have made significant progress. Subsequently, pre-trained language models (PLMs) have been developed for text-to-SQL tasks, achieving promising results. However, as modern databases and user questions grow more complex, PLMs with a limited parameter size often produce incorrect SQL. This necessitates more sophisticated and tailored optimization methods, which restricts the application of PLM-based systems. Recently, large language models (LLMs) have shown significant capabilities in natural language understanding as model scale increases. Thus, integrating LLM-based solutions can bring unique opportunities, improvements, and solutions to text-to-SQL research. In this survey, we provide a comprehensive review of existing LLM-based text-to-SQL studies. Specifically, we offer a brief overview of the technical challenges and evolutionary process of text-to-SQL. Next, we introduce the datasets and metrics designed to evaluate text-to-SQL systems. Subsequently, we present a systematic analysis of recent advances in LLM-based text-to-SQL. Finally, we make a summarization and discuss the remaining challenges in this field and suggest expectations for future research directions. All the related resources of LLM-based, including research papers, benchmarks, and open-source projects, are collected for the community in our repository: https://github.com/DEEP-PolyU/Awesome-LLM-based-Text2SQL.

Cited by

• Hallucination Detection for LLM-based Text-to-SQL Generation via Two-Stage Metamorphic Testing
• From Natural Language to Control Signals: A Conceptual Framework for Semantic Channel Finding in Complex Experimental Infrastructure
• Memelang: An Axial Grammar for LLM-Generated Vector-Relational Queries
• Knowledge Distillation with Structured Chain-of-Thought for Text-to-SQL
• Beyond Text-to-SQL: Autonomous Research-Driven Database Exploration with DAR
• Prompt-to-Parts: Generative AI for Physical Assembly and Scalable Instructions
• OsmT: Bridging OpenStreetMap Queries and Natural Language with Open-source Tag-aware Language Models
• AutoLink: Autonomous Schema Exploration and Expansion for Scalable Schema Linking in Text-to-SQL at Scale
• AskDB: An LLM Agent for Natural Language Interaction with Relational Databases
• DataSage: Multi-agent Collaboration for Insight Discovery with External Knowledge Retrieval, Multi-role Debating, and Multi-path Reasoning
• MARS-SQL: A multi-agent reinforcement learning framework for Text-to-SQL
• Empowering LLMs with Structural Role Inference for Zero-Shot Graph Learning
• Rethinking Text-to-SQL: Dynamic Multi-turn SQL Interaction for Real-world Database Exploration
• MTIR-SQL: Multi-turn Tool-Integrated Reasoning Reinforcement Learning for Text-to-SQL
• State of the Art of LLM-Enabled Interaction with Visualization
• Squrve: A Unified and Modular Framework for Complex Real-World Text-to-SQL Tasks
• Rethinking Schema Linking: A Context-Aware Bidirectional Retrieval Approach for Text-to-SQL
• FinAI Data Assistant: LLM-based Financial Database Query Processing with the OpenAI Function Calling API
• Exploring Database Normalization Effects on SQL Generation
• LinearRAG: Linear Graph Retrieval Augmented Generation on Large-scale Corpora
• LitE-SQL: A Lightweight and Efficient Text-to-SQL Framework with Vector-based Schema Linking and Execution-Guided Self-Correction
• Automated Discovery of Test Oracles for Database Management Systems Using LLMs
• SteinerSQL: Graph-Guided Mathematical Reasoning for Text-to-SQL Generation
• SEFRQO: A Self-Evolving Fine-Tuned RAG-Based Query Optimizer
• DeKeyNLU: Enhancing Natural Language to SQL Generation through Task Decomposition and Keyword Extraction
• Agentic LLMs for Question Answering over Tabular Data
• GradeSQL: Test-Time Inference with Outcome Reward Models for Text-to-SQL Generation from Large Language Models
• Bootstrapping Learned Cost Models with Synthetic SQL Queries
• QueryGenie: Making LLM-Based Database Querying Transparent and Controllable
• MCP2OSC: Parametric Control by Natural Language
• HeSQLNet: A Heterogeneous graph neural network for SQL-to-Text generation
• LoSemB: Logic-Guided Semantic Bridging for Inductive Tool Retrieval
• Multi-agent systems for chemical engineering: A review and perspective
• Automated Code Development for PDE Solvers Using Large Language Models
• You Don't Need Pre-built Graphs for RAG: Retrieval Augmented Generation with Adaptive Reasoning Structures
• Harnessing Temporal Databases for Systematic Evaluation of Factual Time-Sensitive Question-Answering in Large Language Models
• SLM-SQL: An Exploration of Small Language Models for Text-to-SQL
• RASL: Retrieval Augmented Schema Linking for Massive Database Text-to-SQL
• DBMS-LLM Integration Strategies in Industrial and Business Applications: Current Status and Future Challenges
• MemGraphRAG: Memory-based Multi-Agent System for Graph Retrieval-Augmented Generation
• LLM-based Question-Answer Framework for Sensor-driven HVAC System Interaction
• LLM Agents Are the Antidote to Walled Gardens
• FinStat2SQL: A Text2SQL Pipeline for Financial Statement Analysis

Related

• Exploring the Landscape of Text-to-SQL with Large Language Models: Progresses, Challenges and Opportunities
• A Survey of Text-to-SQL in the Era of LLMs: Where are we, and where are we going?
• Large Language Model Enhanced Text-to-SQL Generation: A Survey
• From Natural Language to SQL: Review of LLM-based Text-to-SQL Systems
• Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation