EUVIMEDEUVIMED entdecken
Crossref

SQL-Exchange: Transforming SQL Queries Across Domains

Mohammadreza Daviran, Brian Lin, Davood Rafiei

Proceedings of the VLDB Endowment · 01.02.2026 · 19 (6) · 1291-1304

DOI: 10.14778/3797919.3797935 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the VLDB Endowment, online erschienen am 08.05.2026. Verfasst von Mohammadreza Daviran und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 47 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Zitieren

APA

Daviran, M., Lin, B., & Rafiei, D. (2026). SQL-Exchange: Transforming SQL Queries Across Domains. Proceedings of the VLDB Endowment, 19(6), 1291-1304. https://doi.org/10.14778/3797919.3797935

Vancouver

Daviran M, Lin B, Rafiei D. SQL-Exchange: Transforming SQL Queries Across Domains. Proceedings of the VLDB Endowment. 2026;19(6):1291-1304. doi:10.14778/3797919.3797935

BibTeX
@article{Daviran2026,
  author = {Daviran, Mohammadreza and Lin, Brian and Rafiei, Davood},
  title = {SQL-Exchange: Transforming SQL Queries Across Domains},
  journal = {Proceedings of the VLDB Endowment},
  year = {2026},
  volume = {19},
  number = {6},
  pages = {1291--1304},
  doi = {10.14778/3797919.3797935}
}
Kostenlos starten →