Leveraging Causal Inference for Explainable Automatic Program Repair
Abstract
Deep learning models have made significant progress in automatic program repair. However, the black-box nature of these methods has restricted their practical applications. To address this challenge, this paper presents an interpretable approach for program repair based on sequence-to-sequence models with causal inference and our method is called CPR, short for causal program repair. Our CPR can generate explanations in the process of decision making, which consists of groups of causally related input-output tokens. Firstly, our method infers these relations by querying the model with inputs disturbed by data augmentation. Secondly, it generates a graph over tokens from the responses and solves a partitioning problem to select the most relevant components. The experiments on four programming languages (Java, C, Python, and JavaScript) show that CPR can generate causal graphs for reasonable interpretations and boost the performance of bug fixing in automatic program repair.
Cite
@article{arxiv.2205.13342,
title = {Leveraging Causal Inference for Explainable Automatic Program Repair},
author = {Jianzong Wang and Shijing Si and Zhitao Zhu and Xiaoyang Qu and Zhenhou Hong and Jing Xiao},
journal= {arXiv preprint arXiv:2205.13342},
year = {2022}
}
Comments
This paper has been accepted by IJCNN2022