SQL-Exchange: Transforming SQL Queries Across Domains

TL;DR

SQL-Exchange is a framework that maps SQL queries across different schemas, improving the performance of text-to-SQL systems by enabling better schema adaptation and transfer learning.

Contribution

It introduces a novel schema-mapping framework for SQL queries that enhances in-context learning and fine-tuning in text-to-SQL tasks across diverse schemas.

Findings

Effective across multiple schemas and query types

Improves in-context learning performance

Enhances fine-tuning results

Abstract

We introduce SQL-Exchange, a framework for mapping SQL queries across different database schemas by preserving the source query structure while adapting domain-specific elements to align with the target schema. We investigate the conditions under which such mappings are feasible and beneficial, and examine their impact on enhancing the in-context learning performance of text-to-SQL systems as a downstream task. Our comprehensive evaluation across multiple model families and benchmark datasets -- assessing structural alignment with source queries, execution validity on target databases, and semantic correctness -- demonstrates that SQL-Exchange is effective across a wide range of schemas and query types. Our results further show that both in-context prompting with mapped queries and fine-tuning on mapped data consistently yield higher text-to-SQL performance than using examples drawn directly from the source schema.