Demonstrating SQLBarber: Leveraging Large Language Models to Generate Customized and Realistic SQL Workloads

Summary: SQLBarber is an LLM-driven system that generates customized, realistic SQL workloads without prebuilt templates, guided by natural-language constraints. It derives template specifications and cost distributions from Redshift/Snowflake stats, scales to large workloads, and enables exploring cost-realism trade-offs under user constraints. (summarized by gpt-5-nano on Feb 09 2026)

Paper ID: 7212
Venue: SIGMOD
Year: 2025
Pagerank: 5.3299884e-05
Overall Rank: 9,024 | 38.09%
DOI: 10.1145/3722212.3725101

Incoming Non-self Citations Over Time

Authors

1. Jiale Lao (Cornell University)
2. Immanuel Trummer (Cornell University)

BibTeX Citation

@inproceedings{lao_sigmod25,
        title = {{Demonstrating SQLBarber: Leveraging Large Language Models to Generate Customized and Realistic SQL Workloads}},
        author = {Lao, Jiale and Trummer, Immanuel},
        series = {{SIGMOD} '25},
        booktitle = {Proceedings of the {ACM} {SIGMOD} International Conference on Management of Data},
        publisher = {Association for Computing Machinery},
        doi = {10.1145/3722212.3725101},
        url = {https://dl.acm.org/doi/10.1145/3722212.3725101},
        year = {2025}
}

Incoming Citations (Sorted by Pagerank)

Showing 3 of 3 citing papers.

Rank	Citing Paper	Year	Venue	Pagerank
10,128	Survivorship Bias in Industrial Database Workloads	2026	CIDR	5.093636e-05
10,501	SQLBarber: A System Leveraging Large Language Models to Generate Customized and Realistic SQL Workloads	2026	SIGMOD	5.093636e-05
10,569	Toward Drift-Aware Database Benchmarking	2026	VLDB	5.093636e-05

Outgoing Citations (Sorted by Pagerank)

Showing 5 of 5 cited papers.

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

Rank	Cited Paper	Year	Venue	Pagerank
756	CodeS: Towards Building Open-source Language Models for Text-to-SQL	2024	SIGMOD	0.0001431656
2,298	GPTuner: A Manual-Reading Database Tuning System via GPT-Guided Bayesian Optimization	2024	VLDB	8.7886538e-05
2,408	Why TPC Is Not Enough: An Analysis of the Amazon Redshift Fleet	2024	VLDB	8.6154404e-05
2,521	CodexDB: Synthesizing Code for Query Processing from Natural Language Instructions using GPT-3 Codex	2022	VLDB	8.4729505e-05
5,169	LearnedSQLGen: Constraint-aware SQL Generation using Reinforcement Learning	2022	SIGMOD	6.3349035e-05

Semantically Similar Papers

#	Overall Rank	Paper	Year	Venue
1	11,025	A Demonstration of QueryArtisan: Real-Time Data Lake Analysis via Dynamically Generated Data Manipulation Code	2025	VLDB
2	10,506	This is Going to Sound Crazy, But What If We Used Large Language Models to Boost Automatic Database Tuning Algorithms By Leveraging Prior History? We Will Find Better Configurations More Quickly Than Retraining From Scratch!	2026	SIGMOD
3	3,787	Combining Small Language Models and Large Language Models for Zero-Shot NL2SQL	2024	VLDB
4	9,047	SQL-Factory: A Multi-Agent Framework for High-Quality and Large-Scale SQL Generation	2026	VLDB
5	10,510	NL2SQLBench: A Modular Benchmarking Framework for LLM-Enabled NL2SQL Solutions	2026	VLDB
6	10,122	BenchPress: A Human-in-the-Loop Annotation System for Rapid Text-to-SQL Benchmark Curation	2026	CIDR
7	10,139	Leveraging Query Optimizers to Verify the Soundness of LLM-based Query Rewrites for Real-World Workloads, and More!	2026	CIDR
8	279	Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation	2024	VLDB
9	5,744	SQLStorm: Taking Database Benchmarking into the LLM Era	2025	VLDB
10	10,501	SQLBarber: A System Leveraging Large Language Models to Generate Customized and Realistic SQL Workloads	2026	SIGMOD