@inproceedings{chen-etal-2025-adept,
    title = "{ADEPT}-{SQL}: A High-performance Text-to-{SQL} Application for Real-World Enterprise-Level Databases",
    author = "Chen, Yongnan  and
      Chang, Zhuo  and
      Gu, Shijia  and
      Zong, Yuanhang  and
      Mei, Zhang  and
      Wang, Shiyu  and
      Hezixiang, Hezixiang  and
      Chen, Hongzhi  and
      Wei, Jin  and
      Cui, Bin",
    editor = "Mishra, Pushkar  and
      Muresan, Smaranda  and
      Yu, Tao",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-demo.27/",
    pages = "275--283",
    ISBN = "979-8-89176-253-4",
    abstract = "This paper presents Adept-SQL, a domain-adapted Text2SQL system that addresses critical deployment challenges in professional fields. While modern LLM-based solutions excel on academic benchmarks, we identify three persistent limitations in industrial application: domain-specific knowledge barriers, the schemas complexity in the real world, and the prohibitive computational costs of large LLMs. Our framework introduces two key innovations: a three-stage grounding mechanism combining dynamic terminology expansion, focused schema alignment, and historical query retrieval; coupled with a hybrid prompting architecture that decomposes SQL generation into schema-aware hinting, term disambiguation, and few-shot example incorporation phases. This approach enables efficient execution using smaller open-source LLMs while maintaining semantic precision. Deployed in petroleum engineering domains, our system achieves 97{\%} execution accuracy on real-world databases, demonstrating 49{\%} absolute improvement over SOTA baselines. We release implementation code to advance research in professional Text2SQL systems."
}