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

Autor:	Duan, Yiwen, Yu, Yonghong, Zhao, Xiaoming, Wu, Yichang, Liu, Wenbo
Rok vydání:	2024
Předmět:	Computer Science - Computation and Language Computer Science - Artificial Intelligence Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	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. Comment: COLING-Industry 2025 accepted
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2411.06767 Zobrazit plný text záznamu View this record from Arxiv