loading page

WELL: Applying Bug Detectors to Bug Localization via Weakly Supervised Learning
  • +2
  • Zhuo Li,
  • Huangzhao Zhang,
  • Jia Li,
  • Zhi Jin,
  • Ge Li
Zhuo Li
Peking University
Author Profile
Huangzhao Zhang
Peking University
Author Profile
Jia Li
Peking University
Author Profile
Zhi Jin
Peking University
Author Profile
Ge Li
Peking University

Corresponding Author:lige@pku.edu.cn

Author Profile

Abstract

Bug localization, which is used to help programmers identify the location of bugs in source code, is an essential task in software development. Researchers have already made efforts to harness the powerful deep learning (DL) techniques to automate it. However, training bug localization model is usually challenging because it requires a large quantity of data labeled with the bug’s exact location, which is difficult and time-consuming to collect. By contrast, obtaining bug detection data with binary labels of whether there is a bug in the source code is much simpler. This paper proposes a WEakly supervised bug LocaLization (WELL) method, which only uses the bug detection data with binary labels to train a bug localization model. With CodeBERT finetuned on the buggy-or-not binary labeled data, WELL can address bug localization in a weakly supervised manner. The evaluations on three method-level synthetic datasets and one file-level real-world dataset show that WELL is significantly better than the existing SOTA model in typical bug localization tasks such as variable misuse and other programming bugs.
29 Jun 2023Submitted to Journal of Software: Evolution and Process
30 Jun 2023Submission Checks Completed
30 Jun 2023Assigned to Editor
17 Aug 2023Reviewer(s) Assigned
30 Sep 2023Review(s) Completed, Editorial Evaluation Pending
19 Oct 2023Editorial Decision: Revise Major
11 Nov 20231st Revision Received
11 Nov 2023Submission Checks Completed
11 Nov 2023Assigned to Editor
05 Mar 2024Editorial Decision: Accept