EUVIMEDEUVIMED entdecken
Crossref

SafeQL: Search-based Refinement for Safe and Efficient LLM-based Text-to-SQL

Geonho Lee, Min-Soo Kim

Proceedings of the VLDB Endowment · 01.05.2026 · 19 (9) · 2210-2223

DOI: 10.14778/3819518.3819545 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the VLDB Endowment, online erschienen am 19.08.2026. Verfasst von Geonho Lee und 1 weiteren Autor:innen. Die Arbeit nennt 64 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Large language models (LLMs) have advanced Text-to-SQL by enabling natural language interfaces to databases without task-specific fine-tuning. However, existing LLM-based systems remain unreliable, often generating SQL queries that are invalid under the database schema, referencing non-existent tables, attributes, functions, or values. Such errors persist because interactions with the database management system (DBMS) are typically limited to error messages, leaving it in a largely passive role during query refinement. This paper proposes SafeQL, a search-based refinement paradigm that redefines the role of the DBMS as an active guide in the refinement process. Instead of regenerating entire queries after execution failure, SafeQL interprets DBMS feedback to incrementally repair only the erroneous components. Each refinement step is formulated as a guided search within a safe query space , where candidate queries are progressively validated through DBMS execution, thereby converging to an executable query and preventing repeated regeneration of errors. Experiments on the Bird and Spider benchmarks show that SafeQL significantly improves execution accuracy and efficiency compared to regeneration-based methods.

Zitieren

APA

Lee, G., & Kim, M. (2026). SafeQL: Search-based Refinement for Safe and Efficient LLM-based Text-to-SQL. Proceedings of the VLDB Endowment, 19(9), 2210-2223. https://doi.org/10.14778/3819518.3819545

Vancouver

Lee G, Kim M. SafeQL: Search-based Refinement for Safe and Efficient LLM-based Text-to-SQL. Proceedings of the VLDB Endowment. 2026;19(9):2210-2223. doi:10.14778/3819518.3819545

BibTeX
@article{Lee2026,
  author = {Lee, Geonho and Kim, Min-Soo},
  title = {SafeQL: Search-based Refinement for Safe and Efficient LLM-based Text-to-SQL},
  journal = {Proceedings of the VLDB Endowment},
  year = {2026},
  volume = {19},
  number = {9},
  pages = {2210--2223},
  doi = {10.14778/3819518.3819545}
}
Kostenlos starten →