SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2502.20657 · 2025

Automatic database description generation for Text-to-SQL

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

In the context of the Text-to-SQL task, table and column descriptions are crucial for bridging the gap between natural language and database schema. This report proposes a method for automatically generating effective database descriptions when explicit descriptions are unavailable. The proposed method employs a dual-process approach: a coarse-to-fine process, followed by a fine-to-coarse process. The coarse-to-fine approach leverages the inherent knowledge of LLM to guide the understanding process from databases to tables and finally to columns. This approach provides a holistic understanding of the database structure and ensures contextual alignment. Conversely, the fine-to-coarse approach starts at the column level, offering a more accurate and nuanced understanding when stepping back to the table level. Experimental results on the Bird benchmark indicate that using descriptions generated by the proposed improves SQL generation accuracy by 0.93\% compared to not using descriptions, and achieves 37\% of human-level performance. The source code is publicly available at https://github.com/XGenerationLab/XiYan-DBDescGen.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2502.20657")
get_code_for_paper("2502.20657")
have("2502.20657")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2502.20657.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2502.20657.svg)](https://syntology.ai/paper/2502.20657)

Connect an agent — have() is free.