Exploring Parameter-Efficient Fine-Tuning of Large Language Model on Automated Program Repair
Abstract
Automated Program Repair (APR) aims to fix bugs by generating patches. And existing work has demonstrated that "pre-training and fine-tuning" paradigm enables Large Language Models (LLMs) improve fixing capabilities on APR. However, existing work mainly focuses on Full-Model Fine-Tuning (FMFT) for APR and limited research has been conducted on the execution-based evaluation of Parameter-Efficient Fine-Tuning (PEFT) for APR. Comparing to FMFT, PEFT can reduce computing resource consumption without compromising performance and has been widely adopted to other software engineering tasks.
BibTeX
@inproceedings{Li-al:ASE24,
author = {Guochang Li and
Chen Zhi and
Jialiang Chen and
Junxiao Han and
Shuiguang Deng},
title = {Exploring {Parameter-Efficient} {Fine-Tuning} of Large Language Model on Automated Program Repair},
booktitle = {ASE},
pages = {719--731},
publisher = {{ACM}},
year = {2024},
}