NobleBlocks
Public

ErrorLLM: Modeling SQL Errors for Text-to-SQL Refinement

Published in arXiv (Cornell University) • Mar 4, 2026
NobleIDNI4P471W394R303S530
Authors:
Zijin Hong
,
Hao Chen
,
Zheng Yuan

Abstract

Despite the remarkable performance of large language models (LLMs) in text-to-SQL (SQL generation), correctly producing SQL queries remains challenging during initial generation. The SQL refinement task is subsequently introduced to correct syntactic and semantic errors in generated SQL queries. How...

Subject

Finding related papers...

Discussions

(0)

No comments yet

Be the first to share your thoughts!