Keywords
constraint-aware reranking
schema drift
paired simulation
reproducibility
Abstract
We evaluated constraint-aware reranking for text-to-SQL execution under 21% schema drift. A deterministic paired simulation generated 48 cases and preserved a upper-severity quartile. Mean execution accuracy changed from 0.558 to 0.608; the paired difference was +0.050 (95% interval +0.048 to +0.053). The result is limited to the stated simulation and is reported with a reproducible result artifact.
References
Xie, H., Zhou, X., Yang, J., Shen, S., Wang, Z., Zheng, Y., Xu, T., Shi, Y., Zong, Z., Li, Y., Chen, P., Jiang, J., He, D., Yan, X., & Jiang, J. (2026). SiriusDeliver: Automating Data Warehouse Delivery at Tencent. arXiv. https://doi.org/10.48550/arXiv.2608.09185
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
Jiang, G., Li, W., Yu, C., Zhu, Z., & LI, W. (2025). FGCSQL: A Three-Stage Pipeline for Large Language Model-driven Chinese Text-to-SQL. https://doi.org/10.20944/preprints202502.1059.v1
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
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
-, P. A., -, P. S., -, P. P., -, R. N., & -, P. K. N. (2024). QueryAI: A Conversational Interface for SQL Database Querying Using Natural Language Processing. International Journal For Multidisciplinary Research, 6(6), 30595. https://doi.org/10.36948/ijfmr.2024.v06i06.30595
Mota, F. D. C., Silva, W. D. V. R. D., & Soares, J. D. N. (2026). BENCHMARK DE MODELOS DE LINGUAGEM DE CÓDIGO ABERTO PARA TEXT-TO-SQL EM DADOS ONCOLÓGICOS BRASILEIROS. REMUNOM, 13(14), 1-67. https://doi.org/10.66104/zvzdrv85
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
Chafik, S., Ezzini, S., & Berrada, I. (2025). Enhancing security in text-to-SQL systems: A novel dataset and agent-based framework. Natural Language Processing, 31(6), 1399-1422. https://doi.org/10.1017/nlp.2025.10008
Liang, Z., liu, L., Quan, R., zou, M., li, D., Tang, Y., & qin, H. (2026). Hierarchical Adaptive Reward-based Reinforcement Learning Model for High-Precision Text-to-SQL Generation. https://doi.org/10.2139/ssrn.6767042