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 56 cases and preserved a late-arriving block. Mean execution accuracy changed from 0.499 to 0.544; the paired difference was +0.046 (95% interval +0.044 to +0.048). 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
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
Petrola, L., Brayner, A., & Franco, W. (2025). Heuristic-Guided Text-to-SQL Translation with LLMs: Optimizing Natural Language Interfaces for Relational Databases. Anais do XL Simpósio Brasileiro de Banco de Dados (SBBD 2025), 126-139. https://doi.org/10.5753/sbbd.2025.247037
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
Wang, Y., Chen, Y., Chen, R., Shu, H., Liu, P., & Xu, W. (2026). Enhanced Financial Text-to-SQL Generation via Fine-Grained SQL Refinement. https://doi.org/10.2139/ssrn.6502095
Kim, H., Kim, W., & Kim, W. (2026). GRASP-SQL: Graph Retrieval and Agentic Schema Pruning for Recall-First Text-to-SQL. https://doi.org/10.2139/ssrn.7194451
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
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
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
Mishra, S. K. (2026). Natural Language to SQL at Scale: Integrating OpenAI with Oracle Autonomous Database via SELECT AI. https://doi.org/10.36227/techrxiv.177281023.37874227/v1