BenchPress: A Human-in-the-Loop Annotation System for Rapid Text-to-SQL Benchmark Curation
Summary: BenchPress: a human-in-the-loop RAG+LLM pipeline that generates candidate natural-language utterances for SQL-log queries, letting experts select/edit to rapidly curate domain-specific text-to-SQL benchmarks. Reduces annotation cost and improves evaluation robustness for private enterprise workloads. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Fabian Wenz (Massachusetts Institute of Technology; Technical University of Munich)
- 2. Omar Bouattour (Massachusetts Institute of Technology; Technical University of Munich)
- 3. Devin Yang (Massachusetts Institute of Technology)
- 4. Justin Choi (Massachusetts Institute of Technology)
- 5. Cecil Gregg (Massachusetts Institute of Technology)
- 6. Nesime Tatbul (Intel; Massachusetts Institute of Technology)
- 7. Cagatay Demiralp (Amazon; Massachusetts Institute of Technology)
BibTeX Citation
@inproceedings{wenz_cidr26,
address = {Amsterdam, Netherlands},
series = {{CIDR} '26},
title = {{BenchPress: A Human-in-the-Loop Annotation System for Rapid Text-to-SQL Benchmark Curation}},
booktitle = {Proceedings of the {Conference} on {Innovative} {Data} {Systems} {Research}},
author = {Wenz, Fabian and Bouattour, Omar and Yang, Devin and Choi, Justin and Gregg, Cecil and Tatbul, Nesime and Demiralp, Cagatay},
year = {2026}
}Incoming Citations (Sorted by Pagerank)
Showing 1 of 1 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 10,940 | Bridging NL2SQL for CAN Signal Analytics at NIO: From Externalized Schemas to CTE Pipelines | 2026 | VLDB | 4.9793485e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 1 of 1 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 6,220 | GenEdit: Compounding Operators and Continuous Improvement to Tackle Text-to-SQL in the Enterprise | 2025 | CIDR | 5.8469622e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 9,454 | SQLBarber: A System Leveraging Large Language Models to Generate Customized and Realistic SQL Workloads | 2026 | SIGMOD |
| 2 | 10,831 | PrepBench: How Far Are We from Natural-Language-Driven Data Preparation? | 2026 | VLDB |
| 3 | 4,132 | SQLStorm: Taking Database Benchmarking into the LLM Era | 2025 | VLDB |
| 4 | 5,155 | An In-Depth Benchmarking of Text-to-SQL Systems | 2021 | SIGMOD |
| 5 | 1,866 | ScienceBenchmark: A Complex Real-World Benchmark for Evaluating Natural Language to SQL Systems | 2024 | VLDB |
| 6 | 5,501 | SemBench: A Benchmark for Semantic Query Processing Engines | 2026 | VLDB |
| 7 | 10,893 | Developing and Benchmarking Verification Algorithms to Improve Text-to-SQL Generation | 2026 | VLDB |
| 8 | 174 | Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation | 2024 | VLDB |
| 9 | 7,012 | Reliable Text-to-SQL with Adaptive Abstention | 2025 | SIGMOD |
| 10 | 10,695 | NL2SQLBench: A Modular Benchmarking Framework for LLM-Enabled NL2SQL Solutions | 2026 | VLDB |