EUVIMEDEUVIMED entdecken
Crossref

DeepEye-SQL: A Software-Engineering-Inspired Text-to-SQL Framework

Boyan Li, Chong Chen, Zhujun Xue, Yinan Mei, Yuyu Luo

Proceedings of the ACM on Management of Data · 18.05.2026 · 4 (3) · 1-28

DOI: 10.1145/3802035 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the ACM on Management of Data, online erschienen am 18.05.2026. Verfasst von Boyan Li und 4 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 65 Literaturangaben. Gefördert von: NSF of China, Youth S&T Talent Support Programme of Guangdong Provincial Association for Science and Technology, Young Talent Support Project of Guangzhou Association for Science and Technology.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Large language models (LLMs) have advanced Text-to-SQL, yet existing solutions still fall short of system-level reliability. The limitation is not merely in individual modules -- e.g. , schema linking, reasoning, and verification -- but more critically in the lack of structured orchestration that enforces correctness across the entire workflow. This gap motivates a paradigm shift: treating Text-to-SQL not as free-form language generation but as a software-engineering problem that demands structured, verifiable orchestration. We present D eep E ye -SQL, a software-engineering-inspired framework that reframes Text-to-SQL as the development of a small software program, executed through a verifiable process guided by the Software Development Life Cycle (SDLC). D eep E ye integrates four synergistic stages: it grounds user intent through robust schema linking, enforcing relational closure; enhances fault tolerance with N-version SQL generation; ensures deterministic verification via a ''Syntax-Logic-Quality'' tool-chain that intercepts errors pre-execution; and introduces confidence-aware selection that leverages execution-guided adjudication to resolve ambiguity beyond simple majority voting. Leveraging open-source MoE LLMs (~30B total, ~3B activated parameters) without any fine-tuning, D eep E ye achieves 73.5% execution accuracy on BIRD-Dev, 75.07% on the official BIRD-Test leaderboard, and 89.8% on Spider-Test, outperforming state-of-the-art solutions that rely on larger models or extensive training. This highlights that principled orchestration, rather than LLM scaling alone, is key to achieving system-level reliability in Text-to-SQL.

Förderung

  • NSF of China
  • Youth S&T Talent Support Programme of Guangdong Provincial Association for Science and Technology
  • Young Talent Support Project of Guangzhou Association for Science and Technology
  • Guangdong Basic and Applied Basic Research Foundation
  • Guangzhou Basic and Applied Basic Research Foundation
  • Guangzhou-HKUST(GZ) Joint Funding Program

Zitieren

APA

Li, B., Chen, C., Xue, Z., Mei, Y., & Luo, Y. (2026). DeepEye-SQL: A Software-Engineering-Inspired Text-to-SQL Framework. Proceedings of the ACM on Management of Data, 4(3), 1-28. https://doi.org/10.1145/3802035

Vancouver

Li B, Chen C, Xue Z, Mei Y, Luo Y. DeepEye-SQL: A Software-Engineering-Inspired Text-to-SQL Framework. Proceedings of the ACM on Management of Data. 2026;4(3):1-28. doi:10.1145/3802035

BibTeX
@article{Li2026,
  author = {Li, Boyan and Chen, Chong and Xue, Zhujun and Mei, Yinan and Luo, Yuyu},
  title = {DeepEye-SQL: A Software-Engineering-Inspired Text-to-SQL Framework},
  journal = {Proceedings of the ACM on Management of Data},
  year = {2026},
  volume = {4},
  number = {3},
  pages = {1--28},
  doi = {10.1145/3802035}
}
Kostenlos starten →