CodeFort: Robust Training for Code Generation Models
Yuhao Zhang, Shiqi Wang, Haifeng Qian, Zijian Wang, Mingyue Shang, Linbo Liu, Sanjay Krishna Gouda, Baishakhi Ray
Abstract
Code generation models are not robust to small perturbations, which often lead to incorrect generations and significantly degrade the performance of these models. Although improving the robustness of code generation models is crucial to enhancing user experience in real-world applications, existing research efforts do not address this issue. To fill this gap, we propose CodeFort, a framework to improve the robustness of code generation models, generalizing a large variety of code perturbations to enrich the training data and enabling various robust training strategies, mixing data augmentation, batch augmentation, adversarial logits pairing, and contrastive learning, all carefully designed to support high-throughput training. Extensive evaluations show that we increase the average robust pass rates of baseline CodeGen models from 14.79 to 21.74. We notably decrease the robustness drop rate from 95.02% to 54.95% against code-syntax perturbations.
BibTeX
@inproceedings{zhang-etal-2024-codefort,
title = "{C}ode{F}ort: Robust Training for Code Generation Models",
author = "Zhang, Yuhao and
Wang, Shiqi and
Qian, Haifeng and
Wang, Zijian and
Shang, Mingyue and
Liu, Linbo and
Gouda, Sanjay Krishna and
Ray, Baishakhi and
Ramanathan, Murali Krishna and
Ma, Xiaofei and
Deoras, Anoop",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.303/",
doi = "10.18653/v1/2024.findings-emnlp.303",
pages = "5262--5277"
}