FGCSQL: A Three-Stage Pipeline for Large Language Model-Driven Chinese Text-to-SQL
Electronics · 19.03.2025 · 14 (6) · 1214
DOI: 10.3390/electronics14061214 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics, online erschienen am 19.03.2025. Verfasst von Guanyu Jiang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Xianyang City Key Research and Development Plan Project, Shaanxi Provincial Department and City Joint Key Project, Xi’an City Science and Technology Plan Project.
Abstract (Originalsprache)
Recent advances in large language models have driven major breakthroughs in Text-to-SQL tasks. However, many challenges hinder the use of SQL parsers for cross-language tasks. In this article, we introduce FGCSQL, a novel three-stage pipeline framework to deal with three challenges: cross-language schema linking, SQL parsing potential of LLM, and error propagation in SQL parsers, in which the framework uniquely incorporates a filtering encoder to eliminate irrelevant database schema items, harnessing a pre-trained generative large language model fine-tuned on a carefully structured dataset for enhanced SQL parsing. Finally, a correcting decoder addresses error propagation, culminating in a robust system for semantic parsing tasks. Tested on the CSpider dataset, the FGCSQL showcases a substantial improvement in the exact-set-match (EM) accuracy and execution accuracy (EX) metrics, validating the pipeline’s architecture’s effectiveness in mitigating the challenges typically confronted in Text-to-SQL conversion, especially in cross-lingual contexts. FGCSQL outstrips existing methods in execution precision, indicating the validity of our proposed method.
Förderung
- Xianyang City Key Research and Development Plan Project
- Shaanxi Provincial Department and City Joint Key Project
- Xi’an City Science and Technology Plan Project
- Shanxi Coal Geology Group Co., Ltd. Scientific Research Project
- Shaanxi Provincial Water Conservancy Development Fund Science and Technology Project
Zitieren
APA
Jiang, G., Li, W., Yu, C., Zhu, Z., & Li, W. (2025). FGCSQL: A Three-Stage Pipeline for Large Language Model-Driven Chinese Text-to-SQL. Electronics, 14(6), 1214. https://doi.org/10.3390/electronics14061214
Vancouver
Jiang G, Li W, Yu C, Zhu Z, Li W. FGCSQL: A Three-Stage Pipeline for Large Language Model-Driven Chinese Text-to-SQL. Electronics. 2025;14(6):1214. doi:10.3390/electronics14061214
BibTeX
@article{Jiang2025,
author = {Jiang, Guanyu and Li, Weibin and Yu, Chenglong and Zhu, Zixuan and Li, Wei},
title = {FGCSQL: A Three-Stage Pipeline for Large Language Model-Driven Chinese Text-to-SQL},
journal = {Electronics},
year = {2025},
volume = {14},
number = {6},
pages = {1214},
doi = {10.3390/electronics14061214}
}
EUVIMED