SQLGovernor: An LLM-powered SQL Toolkit for Real World Application

2025/09/10 by Jie Jiang, Jiang, Jie, Siqi Shen +19 · 1 citation
Computer Science · Decision Sciences · #Advanced Database Systems and Queries #Data Quality and Management #Databases (cs.DB) #FOS: Computer and information sciences #Scientific Computing and Data Management

paper · pdf · doi:10.48550/arxiv.2509.08575

openalex publication_date 2025/09/10 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

SQL queries in real world analytical environments, whether written by humans or generated automatically often suffer from syntax errors, inefficiency, or semantic misalignment, especially in complex OLAP scenarios. To address these challenges, we propose SQLGovernor, an LLM powered SQL toolkit that unifies multiple functionalities, including syntax correction, query rewriting, query modification, and consistency verification within a structured framework enhanced by knowledge management. SQLGovernor introduces a fragment wise processing strategy to enable fine grained rewriting and localized error correction, significantly reducing the cognitive load on the LLM. It further incorporates a hybrid self learning mechanism guided by expert feedback, allowing the system to continuously improve through DBMS output analysis and rule validation. Experiments on benchmarks such as BIRD and BIRD CRITIC, as well as industrial datasets, show that SQLGovernor consistently boosts the performance of base models by up to 10%, while minimizing reliance on manual expertise. Deployed in production environments, SQLGovernor demonstrates strong practical utility and effective performance.

Citations

• Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models
• Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows
• Grounding Natural Language to SQL Translation with Data-Based Self-Explanations
• CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQL
• Qwen2.5-Coder Technical Report
• Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge
• CHESS: Contextual Harnessing for Efficient SQL Synthesis
• LLM-R2: A Large Language Model Enhanced Rule-based Rewrite System for Boosting Query Efficiency
• CodeS: Towards Building Open-source Language Models for Text-to-SQL
• Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation
• QueryBooster: Improving SQL Performance Using Middleware Services for Human-Centered Query Rewriting
• Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs
• DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction
• Teaching Large Language Models to Self-Debug
• An End-to-End Learning-based Cost Estimator
• Learned Cardinalities: Estimating Correlated Joins with Deep Learning

Cited by

• BAP-SQL: Budget-Aware Observation Planning for Agentic Text-to-SQL

Related

• SQLfuse: Enhancing Text-to-SQL Performance through Comprehensive LLM Synergy
• AI-Assisted SQL Authoring at Industry Scale
• SWE-SQL: Illuminating LLM Pathways to Solve User SQL Issues in Real-World Applications
• Knowledge-to-SQL: Enhancing SQL Generation with Data Expert LLM
• SQLForge: Synthesizing Reliable and Diverse Data to Enhance Text-to-SQL Reasoning in LLMs