DBScholar

Back to papers

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

Summary: SafeQL makes the DBMS an active search guide for LLM Text-to-SQL refinement. It incrementally repairs erroneous query components in a DBMS-validated safe-query space, improving execution accuracy and efficiency over full-query regeneration. (summarized by gpt-5.6-luna on Aug 17 2026)

Paper ID
hff0418bd99c40d68
Venue
VLDB
Year
2026
Pagerank
4.9793485e-05
Overall Rank
10,780 | 27.53%
DOI
10.14778/3819518.3819545

Incoming Non-self Citations Over Time

No non-self incoming citations found for this paper in this database.

Authors

BibTeX Citation

@article{lee_vldb26,
        title = {{SafeQL: Search-based Refinement for Safe and Efficient LLM-based Text-to-SQL}},
        author = {Lee, Geonho and Kim, Min-Soo},
        journal = {PVLDB},
        series = {{VLDB} '26},
        volume = {19},
        number = {9},
        pages = {2210--2223},
        doi = {10.14778/3819518.3819545},
        url = {https://doi.org/10.14778/3819518.3819545},
        year = {2026}
}

Incoming Citations (Sorted by Pagerank)

Showing 0 of 0 citing papers.

Rank Citing Paper Year Venue Pagerank
Previous Page 1 / 1 Next

Outgoing Citations (Sorted by Pagerank)

Showing 8 of 8 cited papers.

Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.

Previous Page 1 / 1 Next

Semantically Similar Papers