mlsanityData to 7 Oct 2026

An Empirical Study on Learning Bug-Fixing Patches in the Wild via Neural Machine Translation

arXiv 1812.08693 ↗First posted 20 Dec 2018cs.SEcited by 106

Not on the map. Why?

Abstract (arXiv)

Millions of open-source projects with numerous bug fixes are available in code repositories. This proliferation of software development histories can be leveraged to learn how to fix common programming bugs. To explore such a potential, we perform an empirical study to assess the feasibility of using Neural Machine Translation techniques for learning bug-fixing patches for real defects. First, we mine millions of bug-fixes from the change histories of projects hosted on GitHub, in order to extract meaningful examples of such bug-fixes. Next, we abstract the buggy and corresponding fixed code, and use them to train an Encoder-Decoder model able to translate buggy code into its fixed version. In our empirical investigation we found that such a model is able to fix thousands of unique buggy methods in the wild. Overall, this model is capable of predicting fixed patches generated by developers in 9-50% of the cases, depending on the number of candidate patches we allow it to generate. Also, the model is able to emulate a variety of different Abstract Syntax Tree operations and generate candidate patches in a split second.

Key facts. Cited by 106 papers in the map (data through 7 Oct 2026). First posted on arXiv 20 Dec 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 18; 2022: 23; 2023: 25; 2024: 18; 2025: 10; 2026: 12.

106 papers.

Sort:

By area:

  1. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  2. 2021CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generationcited by 890
  3. 2021CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generationcited by 732
  4. 2021Unified Pre-training for Program Understanding and Generationcited by 361
  5. 2021CodeNet: A Large-Scale AI for Code Dataset for Learning a Diversity of Coding Taskscited by 199
  6. 2024Large Language Models for Education: A Survey and Outlookcited by 185
  7. 2021Examining Zero-Shot Vulnerability Repair with Large Language Modelscited by 105
  8. 2022Automating Code Review Activities by Large-Scale Pre-trainingcited by 98
  9. 2024RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graphcited by 88
  10. 2021CURE: Code-Aware Neural Machine Translation for Automatic Program Repaircited by 85
  11. 2021Leveraging Automated Unit Tests for Unsupervised Code Translationcited by 82
  12. 2021DOBF: A Deobfuscation Pre-Training Objective for Programming Languagescited by 68
38 more
  1. 2022CoCoMIC: Code Completion By Jointly Modeling In-file and Cross-file Contextcited by 64
  2. 2023Copiloting the Copilots: Fusing Large Language Models with Completion Engines for Automated Program Repaircited by 55
  3. 2022NatGen: Generative pre-training by "Naturalizing" source codecited by 53
  4. 2022CodeAttack: Code-Based Adversarial Attacks for Pre-trained Programming Language Modelscited by 48
  5. 2023LLaMA-Reviewer: Advancing Code Review Automation with Large Language Models through Parameter-Efficient Fine-Tuningcited by 47
  6. 2023xCodeEval: A Large Scale Multilingual Multitask Benchmark for Code Understanding, Generation, Translation and Retrievalcited by 46
  7. 2024Recent Advances of Foundation Language Models-based Continual Learning: A Surveycited by 46
  8. 2022CoditT5: Pretraining for Source Code and Natural Language Editingcited by 45
  9. 2023The Shifted and The Overlooked: A Task-oriented Investigation of User-GPT Interactionscited by 45
  10. 2023RAP-Gen: Retrieval-Augmented Patch Generation with CodeT5 for Automatic Program Repaircited by 43
  11. 2023CodeScope: An Execution-based Multilingual Multitask Multidimensional Benchmark for Evaluating LLMs on Code Understanding and Generationcited by 39
  12. 2021Neural Transfer Learning for Repairing Security Vulnerabilities in C Codecited by 36
  13. 2023Natural Language Generation and Understanding of Big Code for AI-Assisted Programming: A Reviewcited by 32
  14. 2024AST-T5: Structure-Aware Pretraining for Code Generation and Understandingcited by 32
  15. 2022ERNIE-Code: Beyond English-Centric Cross-lingual Pretraining for Programming Languagescited by 29
  16. 2023Better patching using LLM prompting, via Self-Consistencycited by 29
  17. 2023Large Language Models of Code Fail at Completing Code with Potential Bugscited by 28
  18. 2021On Multi-Modal Learning of Editing Source Codecited by 25
  19. 2021A Survey on Machine Learning Techniques for Source Code Analysiscited by 23
  20. 2023Exploring Continual Learning for Code Generation Modelscited by 22
  21. 2022Deep Learning Meets Software Engineering: A Survey on Pre-Trained Models of Source Codecited by 20
  22. 2023Multi-target Backdoor Attacks for Code Pre-trained Modelscited by 19
  23. 2021Generating Bug-Fixes Using Pretrained Transformerscited by 18
  24. 2021DeepDebug: Fixing Python Bugs Using Stack Traces, Backtranslation, and Code Skeletonscited by 17
  25. 2023CrossCodeBench: Benchmarking Cross-Task Generalization of Source Code Modelscited by 16
  26. 2023ITER: Iterative Neural Repair for Multi-Location Patchescited by 16
  27. 2023Better Context Makes Better Code Language Models: A Case Study on Function Call Argument Completioncited by 14
  28. 2023A Static Evaluation of Code Completion by Large Language Modelscited by 14
  29. 2023Benchmarking Causal Study to Interpret Large Language Models for Source Codecited by 14
  30. 2022A Survey on Pretrained Language Models for Neural Code Intelligencecited by 13
  31. 2023KNOD: Domain Knowledge Distilled Tree Decoder for Automated Program Repaircited by 13
  32. 2021Learning C to x86 Translation: An Experiment in Neural Compilationcited by 12
  33. 2023Toward a Theory of Causation for Interpreting Neural Code Modelscited by 12
  34. 2022Improving Automated Program Repair with Domain Adaptationcited by 10
  35. 2023RunBugRun -- An Executable Dataset for Automated Program Repaircited by 10
  36. 2026Agent-as-a-Router: Agentic Model Routing for Coding Taskscited by 10
  37. 2024PythonSaga: Redefining the Benchmark to Evaluate Code Generating LLMscited by 9
  38. 2022Fix Bugs with Transformer through a Neural-Symbolic Edit Grammarcited by 8

50 most cited of 106 All 106 (JSON)