Schema on the Inside: A Two-Phase Fine-Tuning Method for High-Efficiency Text-to-SQL at Scale
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (47) · 40110-40117
DOI: 10.1609/aaai.v40i47.41446 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Chinmay Soni und 3 weiteren Autor:innen.
Abstract (Originalsprache)
Applying large, proprietary API-based language models to text-to-SQL tasks poses a significant industry challenge: reliance on massive, schema-heavy prompts results in prohibitive per-token API costs and high latency, hindering scalable production deployment. We present a specialized, self-hosted 8B-parameter model designed for a conversational bot in CriQ, a sister app to Dream11—India’s largest fantasy sports platform with over 250 million users—that answers user queries about cricket statistics. Our novel two-phase supervised fine-tuning approach enables the model to internalize the entire database schema, eliminating the need for long-context prompts. This reduces input tokens by over 99%, from a 17k-token baseline to fewer than 100, and replaces costly external API calls with efficient local inference. The resulting system achieves 98.4% execution success and 92.5% semantic accuracy, substantially outperforming a prompt-engineered baseline using Google’s Gemini Flash 2.0 (95.6% execution, 89.4% semantic accuracy). These results demonstrate a practical path toward high-precision, low-latency text-to-SQL applications using domain-specialized, self-hosted language models in large-scale production environments.
Zitieren
APA
Soni, C., Chourasia, S., Kumar, G., & Kapoor, H. (2026). Schema on the Inside: A Two-Phase Fine-Tuning Method for High-Efficiency Text-to-SQL at Scale. Proceedings of the AAAI Conference on Artificial Intelligence, 40(47), 40110-40117. https://doi.org/10.1609/aaai.v40i47.41446
Vancouver
Soni C, Chourasia S, Kumar G, Kapoor H. Schema on the Inside: A Two-Phase Fine-Tuning Method for High-Efficiency Text-to-SQL at Scale. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(47):40110-40117. doi:10.1609/aaai.v40i47.41446
BibTeX
@article{Soni2026,
author = {Soni, Chinmay and Chourasia, Shivam and Kumar, Gaurav and Kapoor, Hitesh},
title = {Schema on the Inside: A Two-Phase Fine-Tuning Method for High-Efficiency Text-to-SQL at Scale},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {47},
pages = {40110--40117},
doi = {10.1609/aaai.v40i47.41446}
}
EUVIMED