PRISM: Navigating Cost–Accuracy Trade-offs for NL2SQL
Proceedings of the ACM on Management of Data · 02.04.2026 · 4 (1) · 1-27
DOI: 10.1145/3786679 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the ACM on Management of Data, online erschienen am 07.04.2026. Verfasst von Gaurav Tarlok Kakkar und 4 weiteren Autor:innen. Die Arbeit nennt 55 Literaturangaben. Gefördert von: National Science Foundation.
Abstract (Originalsprache)
Large language models (LLMs) have achieved strong performance on natural language to SQL (NL2SQL) tasks, but their practical effectiveness depends on tuning a complex pipeline of interacting components. Real-world deployments must navigate a critical trade-off between execution accuracy and monetary cost, a factor that has been largely overlooked by prior work focused primarily on maximizing accuracy. Navigating this trade-off is non-trivial: the ideal configuration of components (e.g., LLM, prompting strategy, schema linking) is not only interdependent but also highly sensitive to the target database schema. This creates a challenging, schema-aware configuration tuning problem that lacks a systematic solution. We present PRISM, a framework that systematically identifies high-accuracy, cost-efficient NL2SQL configurations tailored to each schema. Adopting an optimize-then-deploy strategy, PRISM first uses cost-aware Bayesian Optimization in an offline phase to efficiently explore the configuration space and curate a pool of high-performing pipelines. In an online phase, it deploys these configurations either as a single, cost-effective candidate or as an ensemble to maximize accuracy. Experiments on the BIRD benchmark demonstrate that PRISM achieves 69.48% execution accuracy in the single-candidate setting, improving accuracy by 2.34% over the strongest baseline while reducing cost by 92%. In the ensemble setting, PRISM boosts accuracy further to 74.9%.
Förderung
- National Science Foundation
Zitieren
APA
Kakkar, G. T., Chung, Y., Özcan, F., Mussmann, S., & Arulraj, J. (2026). PRISM: Navigating Cost–Accuracy Trade-offs for NL2SQL. Proceedings of the ACM on Management of Data, 4(1), 1-27. https://doi.org/10.1145/3786679
Vancouver
Kakkar GT, Chung Y, Özcan F, Mussmann S, Arulraj J. PRISM: Navigating Cost–Accuracy Trade-offs for NL2SQL. Proceedings of the ACM on Management of Data. 2026;4(1):1-27. doi:10.1145/3786679
BibTeX
@article{Kakkar2026,
author = {Kakkar, Gaurav Tarlok and Chung, Yeounoh and Özcan, Fatma and Mussmann, Steve and Arulraj, Joy},
title = {PRISM: Navigating Cost–Accuracy Trade-offs for NL2SQL},
journal = {Proceedings of the ACM on Management of Data},
year = {2026},
volume = {4},
number = {1},
pages = {1--27},
doi = {10.1145/3786679}
}
EUVIMED