Keywords
constraint-aware reranking
schema drift
paired simulation
reproducibility
Abstract
We evaluated constraint-aware reranking for text-to-SQL execution under 42% schema drift. A deterministic paired simulation generated 56 cases and preserved a upper-severity quartile. Mean execution accuracy changed from 0.537 to 0.582; the paired difference was +0.045 (95% interval +0.043 to +0.047). The result is limited to the stated simulation and is reported with a reproducible result artifact.
References
Zhang, B., Xie, H., Du, P., Chen, J., Cao, P., Chen, Y., Liu, S., Liu, K., & Zhao, J. (2023). ZhuJiu: A Multi-dimensional, Multi-faceted Chinese Benchmark for Large Language Models. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, 479-494. https://doi.org/10.18653/v1/2023.emnlp-demo.44
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
Nugraha, G. P., Suadaa, L. H., Wilantika, N., & Maghfiroh, L. R. (2024). Pengembangan Aplikasi Chatbot dengan Large Language Model untuk Text-to-SQL Generation. Seminar Nasional Official Statistics, 2024(1), 831-840. https://doi.org/10.34123/semnasoffstat.v2024i1.2252
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
Rapolu, N. K. (2023). MIGRATION OF LEGACY DATABASE ORACLE/MS SQL TO HANA DATABASE TO IMPROVE REAL-TIME ONLINE ANALYTICAL PROCESSING AND ONLINE TRANSACTION PROCESSING FROM ONE DATA MODEL. International Scientific Journal of Engineering and Management, 02(03), 1-7. https://doi.org/10.55041/isjem00215
Jawale, D., Shelke, S., & Yadav, S. (2026). Analyzing the Impact of Database Architecture on Performance: SQL vs NoSQL. International Journal of Mathematics And Computer Research, 14(03). https://doi.org/10.47191/ijmcr/v14ispc3.13
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
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
Gao, D., Wang, H., Li, Y., Sun, X., Qian, Y., Ding, B., & Zhou, J. (2024). Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation. Proceedings of the VLDB Endowment, 17(5), 1132-1145. https://doi.org/10.14778/3641204.3641221