Keywords
constraint-aware reranking
schema drift
paired simulation
reproducibility
Abstract
We evaluated constraint-aware reranking for text-to-SQL execution under 17% schema drift. A deterministic paired simulation generated 48 cases and preserved a median slice. Mean execution accuracy changed from 0.559 to 0.604; 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
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
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
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
Yuan, H., Tang, X., Chen, K., Shou, L., Chen, G., & Li, H. (2025). CogSQL: A Cognitive Framework for Enhancing Large Language Models in Text-to-SQL Translation. Proceedings of the AAAI Conference on Artificial Intelligence, 39(24), 25778-25786. https://doi.org/10.1609/aaai.v39i24.34770
Marshan, A., Almutairi, A. N., Ioannou, A., Bell, D., Monaghan, A., & Arzoky, M. (2024). MedT5SQL: a transformers-based large language model for text-to-SQL conversion in the healthcare domain. Frontiers in Big Data, 7, 1371680. https://doi.org/10.3389/fdata.2024.1371680
Jain, K. (2024). Experimental Evaluation: Is NoSQL better than SQL Database?. https://doi.org/10.22541/au.172498858.84181818/v1
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
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
Beckmann, S., Wiesner, K., Tebruegge, C., & Grum, M. (2026). Combining Text-to-SQL and Large Language Models for Maintenance Decision Support. https://doi.org/10.2139/ssrn.7103027
Zhou, F., Hu, S., Du, X., Li, N., Zhou, T., Zhao, Y., Shang, S., Ling, X., & Zhu, H. (2025). Nabil: A Text-to-SQL Model Based on Brain-Inspired Computing Techniques and Large Language Modeling. Electronics, 14(19), 3910. https://doi.org/10.3390/electronics14193910