English

PDC & DM-SFT: A Road for LLM SQL Bug-Fix Enhancing

Computation and Language 2024-11-12 v1 Artificial Intelligence Machine Learning

Abstract

Code Large Language Models (Code LLMs), such as Code llama and DeepSeek-Coder, have demonstrated exceptional performance in the code generation tasks. However, most existing models focus on the abilities of generating correct code, but often struggle with bug repair. We introduce a suit of methods to enhance LLM's SQL bug-fixing abilities. The methods are mainly consisted of two parts: A Progressive Dataset Construction (PDC) from scratch and Dynamic Mask Supervised Fine-tuning (DM-SFT). PDC proposes two data expansion methods from the perspectives of breadth first and depth first respectively. DM-SFT introduces an efficient bug-fixing supervised learning approach, which effectively reduce the total training steps and mitigate the "disorientation" in SQL code bug-fixing training. In our evaluation, the code LLM models trained with two methods have exceeds all current best performing model which size is much larger.

Keywords

Cite

@article{arxiv.2411.06767,
  title  = {PDC & DM-SFT: A Road for LLM SQL Bug-Fix Enhancing},
  author = {Yiwen Duan and Yonghong Yu and Xiaoming Zhao and Yichang Wu and Wenbo Liu},
  journal= {arXiv preprint arXiv:2411.06767},
  year   = {2024}
}

Comments

COLING-Industry 2025 accepted

R2 v1 2026-06-28T19:55:13.544Z