mlsanityData to 14 Oct 2026

Applying CodeBERT for Automated Program Repair of Java Simple Bugs

arXiv 2103.11626 ↗First posted 22 Mar 2021cs.SEcited by 44

Not on the map. Why?

Abstract (arXiv)

Software debugging, and program repair are among the most time-consuming and labor-intensive tasks in software engineering that would benefit a lot from automation. In this paper, we propose a novel automated program repair approach based on CodeBERT, which is a transformer-based neural architecture pre-trained on large corpus of source code. We fine-tune our model on the ManySStuBs4J small and large datasets to automatically generate the fix codes. The results show that our technique accurately predicts the fixed codes implemented by the developers in 19-72% of the cases, depending on the type of datasets, in less than a second per bug. We also observe that our method can generate varied-length fixes (short and long) and can fix different types of bugs, even if only a few instances of those types of bugs exist in the training dataset.

Key facts. Cited by 44 papers in the map (data through 14 Oct 2026). First posted on arXiv 22 Mar 2021.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 4; 2022: 11; 2023: 13; 2024: 9; 2025: 5; 2026: 2.

44 papers.

Sort:

By area:

  1. 2022ReACC: A Retrieval-Augmented Code Completion Frameworkcited by 119
  2. 2021CVEfixes: Automated Collection of Vulnerabilities and Their Fixes from Open-Source Softwarecited by 91
  3. 2023Is ChatGPT the Ultimate Programming Assistant -- How far is it?cited by 76
  4. 2023How Effective Are Neural Networks for Fixing Security Vulnerabilitiescited by 52
  5. 2023Large Language Models and Simple, Stupid Bugscited by 45
  6. 2021A Survey on Machine Learning Techniques for Source Code Analysiscited by 24
  7. 2024CigaR: Cost-efficient Program Repair with LLMscited by 15
  8. 2022AutoPruner: Transformer-Based Call Graph Pruningcited by 11
  9. 2022VulCurator: A Vulnerability-Fixing Commit Detectorcited by 11
  10. 2022Who Evaluates the Evaluators? On Automatic Metrics for Assessing AI-based Offensive Code Generatorscited by 11
  11. 2022Detect-Localize-Repair: A Unified Framework for Learning to Debug with CodeT5cited by 10
  12. 2024Large Language Model Evaluation Via Multi AI Agents: Preliminary resultscited by 10
32 more
  1. 2023Automating Code-Related Tasks Through Transformers: The Impact of Pre-trainingcited by 8
  2. 2022Is this Change the Answer to that Problem? Correlating Descriptions of Bug and Code Changes for Evaluating Patch Correctnesscited by 7
  3. 2024Investigating the Performance of Language Models for Completing Code in Functional Programming Languages: a Haskell Case Studycited by 7
  4. 2021Improving Code Autocompletion with Transfer Learningcited by 6
  5. 2022DexBERT: Effective, Task-Agnostic and Fine-grained Representation Learning of Android Bytecodecited by 6
  6. 2023FlakyFix: Using Large Language Models for Predicting Flaky Test Fix Categories and Test Code Repaircited by 6
  7. 2023Automating the Correctness Assessment of AI-generated Code for Security Contextscited by 6
  8. 2021Improving Stack Overflow question title generation with copying enhanced CodeBERT model and bi-modal informationcited by 5
  9. 2023Multi-Granularity Detector for Vulnerability Fixescited by 4
  10. 2023ConDefects: A New Dataset to Address the Data Leakage Concern for LLM-based Fault Localization and Program Repaircited by 4
  11. 2024AI for DevSecOps: A Landscape and Future Opportunitiescited by 4
  12. 2022Test2Vec: An Execution Trace Embedding for Test Case Prioritizationcited by 3
  13. 2022Using Developer Discussions to Guide Fixing Bugs in Softwarecited by 3
  14. 2023Enhancing Robustness of AI Offensive Code Generators via Data Augmentationcited by 3
  15. 2024Enhancing AI-based Generation of Software Exploits with Contextual Informationcited by 3
  16. 2024LecPrompt: A Prompt-based Approach for Logical Error Correction with CodeBERTcited by 3
  17. 2022Diverse Title Generation for Stack Overflow Posts with Multiple Sampling Enhanced Transformercited by 2
  18. 2024Automated Code Fix Suggestions for Accessibility Issues in Mobile Appscited by 2
  19. 2024CodePurify: Defend Backdoor Attacks on Neural Code Models via Entropy-based Purificationcited by 2
  20. 2025SDLog: A Deep Learning Framework for Detecting Sensitive Information in Software Logscited by 2
  21. 2022Learning to Learn to Predict Performance Regressions in Production at Metacited by 1
  22. 2023Towards Automatically Addressing Self-Admitted Technical Debt: How Far Are We?cited by 1
  23. 2023Exploring Large Language Models in Resolving Environment-Related Crash Bugs: Localizing and Repairingcited by 1
  24. 2023Characterizing and Classifying Developer Forum Posts with their Intentionscited by 1
  25. 2025Call Me Maybe: Enhancing JavaScript Call Graph Construction using Graph Neural Networkscited by 1
  26. 2025Accelerating Automatic Program Repair with Dual Retrieval-Augmented Fine-Tuning and Patch Generation on Large Language Modelscited by 1
  27. 2023Towards Automatic Support of Software Model Evolution with Large Language~Modelscited by 0
  28. 2024A Data-to-Product Multimodal Conceptual Framework to Achieve Automated Software Evolution for Context-rich Intelligent Applicationscited by 0
  29. 2025T3: Multi-level Tree-based Automatic Program Repair with Large Language Modelscited by 0
  30. 2025Resource-Efficient Automatic Software Vulnerability Assessment via Knowledge Distillation and Particle Swarm Optimizationcited by 0
  31. 2026Improving MPI Error Detection and Repair with Large Language Models and Bug Referencescited by 0
  32. 2026MultiFixer: A Coordinator-Proposer Based Multi-Agent Framework For Fixing Multi-Hunk Bugscited by 0