SQLBarber: A System Leveraging Large Language Models to Generate Customized and Realistic SQL Workloads
Summary: SQLBarber uses LLMs to synthesize realistic, customizable SQL workloads from natural-language constraints, avoiding hand-written templates. It couples self-correcting template generation with Bayesian cost targeting to match production-derived cardinality/plan-cost distributions and scales to large benchmark synthesis.
(summarized by gpt-5-mini on Apr 11 2026)
@inproceedings{lao_sigmod26,
title = {{SQLBarber: A System Leveraging Large Language Models to Generate Customized and Realistic SQL Workloads}},
author = {Lao, Jiale and Trummer, Immanuel},
series = {{SIGMOD} '26},
booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
publisher = {Association for Computing Machinery},
doi = {10.1145/3786699},
url = {https://dl.acm.org/doi/10.1145/3786699},
year = {2026}
}
Incoming Citations (Sorted by Pagerank)
Showing 0 of 0 citing papers.
Rank
Citing Paper
Year
Venue
Pagerank
PreviousPage 1 / 1Next
Outgoing Citations (Sorted by Pagerank)
Showing 20 of 20 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.