Keywords
constraint-aware reranking
schema drift
paired simulation
reproducibility
Abstract
We evaluated constraint-aware reranking for text-to-SQL execution under 19% schema drift. A deterministic paired simulation generated 64 cases and preserved a late-arriving block. Mean execution accuracy changed from 0.479 to 0.516; the paired difference was +0.037 (95% interval +0.035 to +0.040). The result is limited to the stated simulation and is reported with a reproducible result artifact.
References
Luo, L., Xie, H., Shen, S., Ma, Z., Ling, R., Xu, H., Jiang, H., Chen, D., Li, Y., Chen, P., & Jiang, J. (2026). SIRIUS-SQL: Anchoring Multi-Candidate Text-to-SQL in Execution Feedback. arXiv. https://doi.org/10.48550/arXiv.2606.01246
asadillah, A. (2019). PERANCANGAN DATABASE SISTEM PENJUALAN MENGGUNAKAN DELPHI DAN MICROSOFT SQL SERVER. https://doi.org/10.31219/osf.io/zat5b
Öztürk, E. (2025). Improving Text-to-Sql Conversion for Low-Resource Languages Using Large Language Models. Bitlis Eren Üniversitesi Fen Bilimleri Dergisi, 14(1), 163-178. https://doi.org/10.17798/bitlisfen.1561298
Nascimento, E. R. S., & Casanova, M. A. (2024). Querying Databases with Natural Language: The use of Large Language Models for Text-to-SQL tasks. Anais Estendidos do XXXIX Simpósio Brasileiro de Banco de Dados (SBBD Estendido 2024), 196-201. https://doi.org/10.5753/sbbd_estendido.2024.240552
Maleki, S. E., Pourreza, M., & Rafiei, D. (2026). Confidence Estimation for Text-to-SQL in Large Language Models. Proceedings of the AAAI Conference on Artificial Intelligence, 40(38), 32474-32482. https://doi.org/10.1609/aaai.v40i38.40523
Furniss, P., & Green, A. (2023). SQL/PGQ data model and graph schema. https://doi.org/10.54285/ldbc.qzsk3559
Shamal Chavan and Prof. Sandeep Vishwakarma (2026). Natural Language to SQL (NL2SQL): A Comprehensive Study of Text-to-SQL Systems, Conversational AI for Databases, Enterprise Architectures, Challenges, and Future Directions. International Journal of Advanced Research in Science Communication and Technology, 380. https://doi.org/10.48175/ijarsct-37344
Narasimhan, A., Bhamboo, A. K., Devnathan, A., Vellaisamy, J., & Vijayaraghavan, V. (2024). Benchmarking Large Language Models for NL-to-SQL: A Comprehensive Evaluation of Accuracy, Cost and Throughput. https://doi.org/10.36227/techrxiv.173121325.56335825/v1
Guo, M., & Sun, Y. (2026). A COMPARATIVE STUDY OF LLM - POWERED DATABASE INTERFACES VERSUS TRADITIONAL SQL SYSTEMS FOR INVENTORY MANAGEMENT. NLP & Text Mining, 11-21. https://doi.org/10.5121/csit.2026.160602
Duan, S., Wang, Z., Liu, C., Zhu, Z., Zhang, Y., Han, P., Yan, L., & Peng, Z. (2025). CRED-SQL: Enhancing Real-World Large Scale Database Text-to-SQL Parsing Through Cluster Retrieval and Execution Description. Frontiers in Artificial Intelligence and Applications. https://doi.org/10.3233/faia251337