Guardado en:
Detalles Bibliográficos
Autor principal: Zhang, Wenda
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2505.18929
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915303822196736
author Zhang, Wenda
author_facet Zhang, Wenda
contents The advancements of Large language models (LLMs) have provided great opportunities to text-to-SQL tasks to overcome the main challenges to understand complex domain information and complex database structures in business applications. In this paper, we propose a meta-aware learning framework to integrate domain knowledge, database schema, chain-of-thought reasoning processes, and metadata relationships to improve the SQL generation quality. The proposed framework includes four learning strategies: schema-based learning, Chain-of-Thought (CoT) learning, knowledge-enhanced learning, and key information tokenization. This approach provides a comprehensive understanding of database structure and metadata information towards LLM through fine-tuning to improve its performance on SQL generation within business domains. Through two experimental studies, we have demonstrated the superiority of the proposed methods in execution accuracy, multi-task SQL generation capability, and reduction of catastrophic forgetting.
format Preprint
id arxiv_https___arxiv_org_abs_2505_18929
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Meta-aware Learning in text-to-SQL Large Language Model
Zhang, Wenda
Artificial Intelligence
Computation and Language
The advancements of Large language models (LLMs) have provided great opportunities to text-to-SQL tasks to overcome the main challenges to understand complex domain information and complex database structures in business applications. In this paper, we propose a meta-aware learning framework to integrate domain knowledge, database schema, chain-of-thought reasoning processes, and metadata relationships to improve the SQL generation quality. The proposed framework includes four learning strategies: schema-based learning, Chain-of-Thought (CoT) learning, knowledge-enhanced learning, and key information tokenization. This approach provides a comprehensive understanding of database structure and metadata information towards LLM through fine-tuning to improve its performance on SQL generation within business domains. Through two experimental studies, we have demonstrated the superiority of the proposed methods in execution accuracy, multi-task SQL generation capability, and reduction of catastrophic forgetting.
title Meta-aware Learning in text-to-SQL Large Language Model
topic Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2505.18929