LR-SQL: A Supervised Fine-Tuning Method for Text2SQL Tasks under Low-Resource Scenarios

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Wuzhenghong, Wen, Yongpan, Zhang, Su, Pan, Yuwei, Sun, Pengwei, Lu, Cheng, Ding
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913547428036608
author Wuzhenghong, Wen
Yongpan, Zhang
Su, Pan
Yuwei, Sun
Pengwei, Lu
Cheng, Ding
author_facet Wuzhenghong, Wen
Yongpan, Zhang
Su, Pan
Yuwei, Sun
Pengwei, Lu
Cheng, Ding
contents Large language models revolutionize Text2SQL through supervised fine-tuning, yet a crucial limitation is overlooked: the complexity of databases leads to an increased context length, consequently resulting in higher GPU memory demands for model fine-tuning. To address this issue, we propose LR-SQL. LR-SQL comprises two supervised fine-tuning models: the schema\_link model and the SQL\_generation model, with the schema\_link model serving as the focal point for streamlining the overall process. During the fine-tuning of the schema\_link model, LR-SQL breaks down the complete database into flexible combinations of tables with adjustable quantities, enabling the model to learn the relationships within the entire database from these dispersed slices. Furthermore, to enhance the model's ability to perceive the relationships among various discrete slices during inference, LR-SQL trains the model's Chain-of-Thought capability for this task. Experimental results demonstrate that LR-SQL can reduce the total GPU memory usage by 40\% compared to existing fine-tuning methods, while only losing 2\% of table prediction accuracy in schema\_link task. For the overall Text2SQL task, the Execution Accuracy decrease by 0.6\%.Our project is now available on https://github.com/hongWin/LR-SQL
format Preprint
id arxiv_https___arxiv_org_abs_2410_11457
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle LR-SQL: A Supervised Fine-Tuning Method for Text2SQL Tasks under Low-Resource Scenarios
Wuzhenghong, Wen
Yongpan, Zhang
Su, Pan
Yuwei, Sun
Pengwei, Lu
Cheng, Ding
Databases
Artificial Intelligence
Computation and Language
Information Retrieval
Large language models revolutionize Text2SQL through supervised fine-tuning, yet a crucial limitation is overlooked: the complexity of databases leads to an increased context length, consequently resulting in higher GPU memory demands for model fine-tuning. To address this issue, we propose LR-SQL. LR-SQL comprises two supervised fine-tuning models: the schema\_link model and the SQL\_generation model, with the schema\_link model serving as the focal point for streamlining the overall process. During the fine-tuning of the schema\_link model, LR-SQL breaks down the complete database into flexible combinations of tables with adjustable quantities, enabling the model to learn the relationships within the entire database from these dispersed slices. Furthermore, to enhance the model's ability to perceive the relationships among various discrete slices during inference, LR-SQL trains the model's Chain-of-Thought capability for this task. Experimental results demonstrate that LR-SQL can reduce the total GPU memory usage by 40\% compared to existing fine-tuning methods, while only losing 2\% of table prediction accuracy in schema\_link task. For the overall Text2SQL task, the Execution Accuracy decrease by 0.6\%.Our project is now available on https://github.com/hongWin/LR-SQL
title LR-SQL: A Supervised Fine-Tuning Method for Text2SQL Tasks under Low-Resource Scenarios
topic Databases
Artificial Intelligence
Computation and Language
Information Retrieval
url https://arxiv.org/abs/2410.11457