Source files for 2025 research paper "The Impact of Metadata Configurations on Text-to-SQL Performance: A Comprehensive Analysis"
-
Updated
Jan 27, 2025 - TeX
Source files for 2025 research paper "The Impact of Metadata Configurations on Text-to-SQL Performance: A Comprehensive Analysis"
This project evaluates the performance of large language models (LLMs) on the Text-to-SQL task using the Cantus Database, a specialized collection of metadata on Latin chants. In our work, we demonstrate how LLMs can handle domain-specific queries through prompt engineering without fine-tuning.
Add a description, image, and links to the text-to-sql topic page so that developers can more easily learn about it.
To associate your repository with the text-to-sql topic, visit your repo's landing page and select "manage topics."