RATCHET : Retrieval augmented transformer for program repair

Publication Type

Conference Proceeding Article

Publication Date

10-2024

Abstract

Automated Program Repair (APR) presents the promising momentum of releasing developers from the burden of manual debugging tasks by automatically fixing bugs in various ways. Recent advances in deep learning inspire many works in employing deep learning techniques to fixing buggy programs. However, several challenges remain unaddressed: (1) state-of-the-art fault localization techniques often require additional artifacts, such as bug-triggering test cases or bug reports. These artifacts are not always available in the early development phases; (2) Sequence-to-Sequence model-based APR often requires additional contexts with high quality to generate patches. Yet, it is challenging to identify high-quality contexts that are not common in programs.In this paper, with the redundancy assumption in program repair, we propose a dual deep learning-based APR tool, RATCHET, for localizing (RATCHET-FL) and repairing (Ratchet-PG) buggy programs. Ratchet-FL localizes buggy statements based on the feature learned by a simple BiLSTM model from the code, without any bug-triggering test cases or bug reports. Ratchet-PG relies on our proposed retrieval augmented transformer to learn the historical patches and generate patches for fixing bugs. We evaluate the effectiveness of Ratchet with in-the-lab DrRepair dataset and in-the-wild dataset Ratchet-DS (curated in this work). Our experimental results show that Ratchet outperforms state-of-the-art deep learning approaches on fault localization with 39.8-96.4% accuracy and patch generation with 18.4-46.4% repair accuracy.

Keywords

Automated Program Repair, Deep learning, Bugs fixing, Program repair, Bug-triggering test, Fault localization

Discipline

Artificial Intelligence and Robotics

Research Areas

Intelligent Systems and Optimization

Publication

Proceedings of the 35th IEEE International Symposium on Software Reliability Engineering Workshops (ISSREW 2024) : Tsukuba, Japan, October 28-31

First Page

427

Last Page

438

Identifier

10.1109/ISSRE62328.2024.00048

Publisher

IEEE

City or Country

Tsukuba

Additional URL

https://doi.org/10.1109/ISSRE62328.2024.00048

This document is currently not available here.

Share

COinS