Keywords
constraint-aware reranking
schema drift
paired simulation
reproducibility
Abstract
We evaluated constraint-aware reranking for text-to-SQL execution under 41% schema drift. A deterministic paired simulation generated 72 cases and preserved a rare-condition slice. Mean execution accuracy changed from 0.542 to 0.593; the paired difference was +0.051 (95% interval +0.049 to +0.053). 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
Amel Abdyssalam A Alhaag (2025). Comparison between Database Search Algorithms (SQL and no SQL). مجلة العلوم الشاملة, 9(ملحق 36), 1810-1830. https://doi.org/10.65405/bc8atc11
asadillah, A. (2019). PERANCANGAN DATABASE SISTEM PENJUALAN MENGGUNAKAN DELPHI DAN MICROSOFT SQL SERVER. https://doi.org/10.31219/osf.io/zat5b
Mukti, R. F., Prasetya, A., & Cahyono, T. A. (2026). Deteksi Ill-Formed Natural Language Query Berbasis Rule Pada Model Llm Text-to-SQL Berbahasa Indonesia. HORIZON: Indonesian Journal of Multidisciplinary, 4(4), 5088-5098. https://doi.org/10.54373/hijm.v4i4.6916
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
Rehman, A. U. (2026). FinSight AI: Coupling a Large Language Model with a Live NoSQL Database for Conversational Financial Analytics and Rule-Assisted Fraud Screening. https://doi.org/10.2139/ssrn.7093099
Sangamnerkar, B., & Namdev, S. (2025). Lightweight and Data-Efficient Fine-Tuning of Language Models for Bidirectional Text-to-SQL and SQL-to-Text Tasks: A Systematic Review. Advanced International Journal for Research, 6(6), 2745. https://doi.org/10.63363/aijfr.2025.v06i06.2745
Putra, C., Arlis, S., & Nurcahyo, G. W. (2025). Large Language Model Method as a Translator Indonesian Into SQL Language. Jurnal KomtekInfo, 124-130. https://doi.org/10.35134/komtekinfo.v12i3.658
Wang, Y., Lv, H., & Qian, Y. (2026). CIR-SQL: A Dual-Model Intent Recognition Framework for Chinese Text-to-SQL. AI, 7(3), 91. https://doi.org/10.3390/ai7030091
ŞAHİNASLAN, E., & ŞAHİNASLAN, Ö. (2022). Microsoft SQL Sunucusunda Veritabanı Kurtarma Teknikleri. International Journal of Innovative Engineering Applications, 6(1), 158-169. https://doi.org/10.46460/ijiea.1070325