Keywords
constraint-aware reranking
schema drift
paired simulation
reproducibility
Abstract
We evaluated constraint-aware reranking for text-to-SQL execution under 29% schema drift. A deterministic paired simulation generated 56 cases and preserved a boundary-condition stratum. Mean execution accuracy changed from 0.498 to 0.552; the paired difference was +0.055 (95% interval +0.052 to +0.057). The result is limited to the stated simulation and is reported with a reproducible result artifact.
References
Jiang, J., Xie, H., Shen, S., Shen, Y., Zhang, Z., Lei, M., Zheng, Y., Li, Y., Li, C., Huang, D., Wu, Y., Zhang, W., Cui, B., & Chen, P. (2025). SiriusBI: A Comprehensive LLM-Powered Solution for Data Analytics in Business Intelligence. Proceedings of the VLDB Endowment, 18(12), 4860-4873. https://doi.org/10.14778/3750601.3750610
Nayanakantha, B., Vidanage, K., Nirkhi, S., & Bhattacharyya, S. (2026). A Lightweight and Explainable Conversational AI Framework for Natural Language SQL Learning without Large Language Models. https://doi.org/10.21203/rs.3.rs-9823032/v1
Mellah, Y., Kocaman, V., Ul Haq, H., & Talby, D. (2024). Efficient schema-less text-to-SQL conversion using large language models. Artificial Intelligence in Health, 1(2), 96. https://doi.org/10.36922/aih.2661
Zhou, X., Sun, Z., & Li, G. (2024). DB-GPT: Large Language Model Meets Database. Data Science and Engineering, 9(1), 102-111. https://doi.org/10.1007/s41019-023-00235-6
Hairan, B., & Şahman, M. A. (2026). A comparative evaluation of large language models for detecting SQL injection vulnerabilities in web applications. PeerJ Computer Science, 12, e4015. https://doi.org/10.7717/peerj-cs.4015
Amar Kaygude, Onkar Rajguru, Sandesh Karad, & G.T.Avhad (2025). Text-to-SQL Conversion by using DeepLearning/Machine Learning: IntegratingNatural Language with Database Queries. international journal of engineering technology and management sciences, 9(3), 48-52. https://doi.org/10.46647/ijetms.2025.v09i03.009
Ascoli, B. G., & Choi, J. D. (2025). Advancing Conversational Text-to-SQL: Context Strategies and Model Integration with Large Language Models. Future Internet, 17(11), 527. https://doi.org/10.3390/fi17110527
Cinquin, O. (2024). Steering veridical large language model analyses by correcting and enriching generated database queries: first steps toward ChatGPT bioinformatics. Briefings in Bioinformatics, 26(1), bbaf045. https://doi.org/10.1093/bib/bbaf045
Reichenpfader, D., Müller, H., & Denecke, K. (2023). Large language model-based information extraction from free-text radiology reports: a scoping review protocol. https://doi.org/10.1101/2023.07.28.23292031
Shi, L., Tang, Z., Zhang, N., Zhang, X., & Yang, Z. (2026). A Survey on Employing Large Language Models for Text-to-SQL Tasks. ACM Computing Surveys, 58(2), 1-37. https://doi.org/10.1145/3737873