mlsanityData to 7 Oct 2026

Using Developer Discussions to Guide Fixing Bugs in Software

arXiv 2211.06335 ↗First posted 11 Nov 2022cs.SE cs.CLcited by 3

Not on the map. Why?

Abstract (arXiv)

Automatically fixing software bugs is a challenging task. While recent work showed that natural language context is useful in guiding bug-fixing models, the approach required prompting developers to provide this context, which was simulated through commit messages written after the bug-fixing code changes were made. We instead propose using bug report discussions, which are available before the task is performed and are also naturally occurring, avoiding the need for any additional information from developers. For this, we augment standard bug-fixing datasets with bug report discussions. Using these newly compiled datasets, we demonstrate that various forms of natural language context derived from such discussions can aid bug-fixing, even leading to improved performance over using commit messages corresponding to the oracle bug-fixing commits.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 14 of its 24 references that are in the map. First posted on arXiv 11 Nov 2022.

Builds on

14 of 24 references.

References · 14

  1. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  2. 2018SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processingcited by 1,973
  3. 2021Unified Pre-training for Program Understanding and Generationcited by 361
  4. 2018SequenceR: Sequence-to-Sequence Learning for End-to-End Program Repaircited by 144
  5. 2018An Empirical Study on Learning Bug-Fixing Patches in the Wild via Neural Machine Translationcited by 106
  6. 2021Self-Supervised Bug Detection and Repaircited by 59
  7. 2021Applying CodeBERT for Automated Program Repair of Java Simple Bugscited by 44
  8. 2021Sequence Length is a Domain: Length-based Overfitting in Transformer Modelscited by 34
  9. 2021On Multi-Modal Learning of Editing Source Codecited by 25
  10. 2021On the Evaluation of Commit Message Generation Models: An Experimental Studycited by 20
  11. 2019iFixR: Bug Report driven Program Repaircited by 11
  12. 2019Analysis and Detection of Information Types of Open Source Software Issue Discussionscited by 9
2 more
  1. 2020Learning the Compositional Visual Coherence for Complementary Recommendationscited by 9
  2. 2021Learning to Describe Solutions for Bug Reports Based on Developer Discussionscited by 5

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 1.

3 papers.

  1. 2023Learning Deep Semantics for Test Completioncited by 31
  2. 2023Text-to-SQL Error Correction with Language Models of Codecited by 21
  3. 2024Enhancing Automated Program Repair with Solution Designcited by 8