Scholarlink

<p>To address the strong coupling between schema linking and structural parsing in text-to-SQL tasks for small-scale language models, as well as the neglect of SQL skeleton guidance in existing decoupling methods, this paper proposes SKT-SQL, a multi-stage decoupling framework. The framework redesigns the generation process through a three-stage decoupling mechanism: (1) leveraging a schema decoupler to eliminate irrelevant schema items and reduce semantic noise; (2) predicting query hardness to generate an abstract SQL skeleton, forming a structured template with operator logic; (3) utilizing the skeleton as dynamic prompts to guide a transformer-based seq2seq T5 model in precisely filling specific schema items, followed by execution-guided beam search to derive the final SQL query. This "structure-first, entity-later" paradigm eliminates the need to simultaneously resolve syntactic complexity and schema correlations, significantly reducing cognitive load. Experiments on the Spider 1.0 benchmark show that SKT-SQL-base achieves 80.8% execution accuracy (EX), surpassing the 12<InlineEquation ID="IEq1"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="10844_2025_963_Article_IEq1.gif" Format="GIF" Height="13" Rendition="HTML" Resolution="72" Type="Linedraw" Width="19" /> </InlineMediaObject> <EquationSource Format="TEX">\(\times\)</EquationSource> </InlineEquation> larger T5-3B model by 6.4% and outperforming T5-base by 22.9%. Compared to existing decoupling-based methods, this framework still demonstrates prominent application value, with skeleton prompting notably enhancing small-scale model performance. This study proves that explicit modeling of SQL syntactic skeletons can break through the structured semantic parsing bottleneck of small-scale language models, offering a novel paradigm for database interaction tasks in low-resource scenarios. Our code is available at <a href="https://github.com/JarvenYi/SKT-SQL.">https://github.com/JarvenYi/SKT-SQL.</a></p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

SKT-SQL: multi-decoupling and skeleton prompt framework for text-to-SQL on small-scale LMs

  • 期刊论文

  • 发表日期：

    2025年7月8日

查看全文
  • Jiawen Yi,
  • Guo Chen

摘要

To address the strong coupling between schema linking and structural parsing in text-to-SQL tasks for small-scale language models, as well as the neglect of SQL skeleton guidance in existing decoupling methods, this paper proposes SKT-SQL, a multi-stage decoupling framework. The framework redesigns the generation process through a three-stage decoupling mechanism: (1) leveraging a schema decoupler to eliminate irrelevant schema items and reduce semantic noise; (2) predicting query hardness to generate an abstract SQL skeleton, forming a structured template with operator logic; (3) utilizing the skeleton as dynamic prompts to guide a transformer-based seq2seq T5 model in precisely filling specific schema items, followed by execution-guided beam search to derive the final SQL query. This "structure-first, entity-later" paradigm eliminates the need to simultaneously resolve syntactic complexity and schema correlations, significantly reducing cognitive load. Experiments on the Spider 1.0 benchmark show that SKT-SQL-base achieves 80.8% execution accuracy (EX), surpassing the 12 \(\times\) larger T5-3B model by 6.4% and outperforming T5-base by 22.9%. Compared to existing decoupling-based methods, this framework still demonstrates prominent application value, with skeleton prompting notably enhancing small-scale model performance. This study proves that explicit modeling of SQL syntactic skeletons can break through the structured semantic parsing bottleneck of small-scale language models, offering a novel paradigm for database interaction tasks in low-resource scenarios. Our code is available at https://github.com/JarvenYi/SKT-SQL.