A universal LLM Framework for General Query Refinements

TL;DR

OmniTune is a general framework for refining arbitrary SQL queries using LLM-based optimization by prompting (OPRO) that 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.

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.

Figures (13)

• Figure 1: Initial Scholarship Query $Q$
• Figure 2: OmniTune Workflow & Architecture
• Figure 3: Prompts Formulation
• Figure 4: Examples of textual representations of OmniTune objects
• Figure 5: Datasets used per instance class

Theorems & Definitions (2)

• definition 1: Constraint deviation function
• definition 2: Refinement Subspace