A universal LLM Framework for General Query Refinements

TL;DR

This paper introduces OmniTune, a universal framework leveraging large language models to refine any SQL query by exploring promising modifications and sampling candidates, outperforming existing specialized methods.

Contribution

OmniTune is the first general LLM-based framework capable of refining arbitrary SQL queries across diverse scenarios, extending beyond prior restricted approaches.

Findings

Handles both simple and complex query refinement tasks

Outperforms existing specialized solutions on benchmark tests

Effective in diverse and previously unaddressed scenarios

Abstract

Numerous studies have explored the SQL query refinement problem, where the objective is to minimally modify an input query so that it satisfies a specified set of constraints. However, these works typically target restricted classes of queries or constraints. We present OmniTune, a general framework for refining arbitrary SQL queries using LLM-based optimization by prompting (OPRO). OmniTune employs a two-step OPRO scheme that explores promising refinement subspaces and samples candidates within them, supported by concise history and skyline summaries for effective feedback. Experiments on a comprehensive benchmark demonstrate that OmniTune handles both previously studied refinement tasks and more complex scenarios beyond the scope of existing solutions.