@inproceedings{hoang-etal-2025-distill,
    title = "Distill-{C}: Enhanced {NL}2{SQL} via Distilled Customization with {LLM}s",
    author = "Hoang, Cong Duy Vu  and
      Tangari, Gioacchino  and
      Lanfranchi, Clemence  and
      Guo, Dalu  and
      Cayet, Paul  and
      Siu, Steve  and
      Dharmasiri, Don  and
      Li, Yuan-Fang  and
      Duong, Long  and
      Hilloulin, Damien  and
      Patra, Rhicheek  and
      Hong, Sungpack  and
      Chafi, Hassan",
    editor = "Chen, Weizhu  and
      Yang, Yi  and
      Kachuee, Mohammad  and
      Fu, Xue-Yong",
    booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 3: Industry Track)",
    month = apr,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2025.naacl-industry.64/",
    pages = "833--848",
    ISBN = "979-8-89176-194-0",
    abstract = "The growing adoption of large language models (LLMs) in business applications has amplified interest in Natural Language to SQL (NL2SQL) solutions, in which there is competing demand for high performance and efficiency. Domain- and customer-specific requirements further complicate the problem. To address this conundrum, we introduce Distill-C, a distilled customization framework tailored for NL2SQL tasks. Distill-C utilizes large teacher LLMs to produce high-quality synthetic data through a robust and scalable pipeline. Finetuning smaller and open-source LLMs on this synthesized data enables them to rival or outperform teacher models an order of magnitude larger. Evaluated on multiple challenging benchmarks, Distill-C achieves an average improvement of 36{\%} in execution accuracy compared to the base models from three distinct LLM families. Additionally, on three internal customer benchmarks, Distill-C demonstrates a 22.6{\%} performance improvement over the base models. Our results demonstrate that Distill-C is an effective, high-performing and generalizable approach for deploying lightweight yet powerful NL2SQL models, delivering exceptional accuracies while maintaining low computational cost."
}