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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Jiang, Jie, Shen, Siqi, Xie, Haining, Li, Yang, Shen, Yu, Huang, Danqing, Qian, Bo, Wu, Yinjun, Zhang, Wentao, Cui, Bin, Chen, Peng
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914037808234496
author Jiang, Jie
Shen, Siqi
Xie, Haining
Li, Yang
Shen, Yu
Huang, Danqing
Qian, Bo
Wu, Yinjun
Zhang, Wentao
Cui, Bin
Chen, Peng
author_facet Jiang, Jie
Shen, Siqi
Xie, Haining
Li, Yang
Shen, Yu
Huang, Danqing
Qian, Bo
Wu, Yinjun
Zhang, Wentao
Cui, Bin
Chen, Peng
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2509_08575
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SQLGovernor: An LLM-powered SQL Toolkit for Real World Application
Jiang, Jie
Shen, Siqi
Xie, Haining
Li, Yang
Shen, Yu
Huang, Danqing
Qian, Bo
Wu, Yinjun
Zhang, Wentao
Cui, Bin
Chen, Peng
Databases
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.
title SQLGovernor: An LLM-powered SQL Toolkit for Real World Application
topic Databases
url https://arxiv.org/abs/2509.08575