Metraipolis › archive › dc_326db32457ad
SafeQL: Search-based Refinement for Safe and Efficient LLM-based Text-to-SQL — arXiv:2608.09260
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.09260
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T09:14:24.324Z
- SHA-256 of the archived text
51f843d044d2feb9de6a60f4933a45cd2e939b52000a117fbe79429e7947a4e0- Stable URL of this page
https://metraipolis.com/documento/dc_326db32457ad
How to cite
SafeQL: Search-based Refinement for Safe and Efficient LLM-based Text-to-SQL — arXiv:2608.09260 — arXiv (en), https://arxiv.org/abs/2608.09260 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_326db32457ad (Metraipolis archive dc_326db32457ad, sha256 51f843d044d2feb9de6a60f4933a45cd2e939b52000a117fbe79429e7947a4e0)
BibTeX
@misc{dc326db32457ad,
title = {SafeQL: Search-based Refinement for Safe and Efficient LLM-based Text-to-SQL — arXiv:2608.09260},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.09260},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_326db32457ad; sha256 51f843d044d2feb9de6a60f4933a45cd2e939b52000a117fbe79429e7947a4e0},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.09260. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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, \textit{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 \textit{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.
Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-11 in cs.DB).
Categorie arXiv: Databases (cs.DB) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.09260 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-19T09:12:27.038Z dalla pagina https://arxiv.org/catchup/cs.DB/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).