mlsanityData to 7 Oct 2026

CURE: Code-Aware Neural Machine Translation for Automatic Program Repair

arXiv 2103.00073 ↗First posted 26 Feb 2021cs.SE cs.AI cs.LGcited by 85

Not on the map. Why?

Abstract (arXiv)

Automatic program repair (APR) is crucial to improve software reliability. Recently, neural machine translation (NMT) techniques have been used to fix software bugs automatically. While promising, these approaches have two major limitations. Their search space often does not contain the correct fix, and their search strategy ignores software knowledge such as strict code syntax. Due to these limitations, existing NMT-based techniques underperform the best template-based approaches. We propose CURE, a new NMT-based APR technique with three major novelties. First, CURE pre-trains a programming language (PL) model on a large software codebase to learn developer-like source code before the APR task. Second, CURE designs a new code-aware search strategy that finds more correct fixes by focusing on compilable patches and patches that are close in length to the buggy code. Finally, CURE uses a subword tokenization technique to generate a smaller search space that contains more correct fixes. Our evaluation on two widely-used benchmarks shows that CURE correctly fixes 57 Defects4J bugs and 26 QuixBugs bugs, outperforming all existing APR techniques on both benchmarks.

Key facts. Cited by 85 papers in the map (data through 7 Oct 2026). Builds on 36 of its 89 references that are in the map. First posted on arXiv 26 Feb 2021.

Builds on

36 of 89 references.

References · 36

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  4. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,898
  5. 2019fairseq: A Fast, Extensible Toolkit for Sequence Modelingcited by 1,486
  6. 2017Convolutional Sequence to Sequence Learningcited by 550
  7. 2018code2vec: Learning Distributed Representations of Codecited by 249
  8. 2017A Survey of Machine Learning for Big Code and Naturalnesscited by 220
  9. 2018code2seq: Generating Sequences from Structured Representations of Codecited by 177
  10. 2018SequenceR: Sequence-to-Sequence Learning for End-to-End Program Repaircited by 144
  11. 2018An Empirical Study on Learning Bug-Fixing Patches in the Wild via Neural Machine Translationcited by 106
  12. 2019Neural Machine Translation: A Review and Surveycited by 99
24 more
  1. 2016A Convolutional Attention Network for Extreme Summarization of Source Codecited by 90
  2. 2016Latent Predictor Networks for Code Generationcited by 73
  3. 2019TBar: Revisiting Template-based Automated Program Repaircited by 64
  4. 2020Multi-task Learning based Pre-trained Language Model for Code Completioncited by 58
  5. 2018CODIT: Code Editing with Tree-Based Neural Modelscited by 40
  6. 2020Synthesize, Execute and Debug: Learning to Repair for Neural Program Synthesiscited by 39
  7. 2020CC2Vec: Distributed Representations of Code Changescited by 38
  8. 2018Nopol: Automatic Repair of Conditional Statement Bugs in Java Programscited by 32
  9. 2017ARJA: Automated Repair of Java Programs via Multi-Objective Genetic Programmingcited by 26
  10. 2019On the use of BERT for Neural Machine Translationcited by 23
  11. 2018FixMiner: Mining Relevant Fix Patterns for Automated Program Repaircited by 22
  12. 2018AVATAR : Fixing Semantic Bugs with Fix Patterns of Static Analysis Violationscited by 22
  13. 2020Evaluating Representation Learning of Code Changes for Predicting Patch Correctness in Program Repaircited by 22
  14. 2020Learning Semantic Program Embeddings with Graph Interval Neural Networkcited by 20
  15. 2018Practical Program Repair via Bytecode Mutationcited by 19
  16. 2020Patching as Translation: the Data and the Metaphorcited by 18
  17. 2020On the Efficiency of Test Suite based Program Repair: A Systematic Assessment of 16 Automated Repair Systems for Java Programscited by 16
  18. 2016Precise Condition Synthesis for Program Repaircited by 13
  19. 2018You Cannot Fix What You Cannot Find! An Investigation of Fault Localization Bias in Benchmarking Automated Program Repair Systemscited by 13
  20. 2019Bears: An Extensible Java Bug Benchmark for Automatic Program Repair Studiescited by 13
  21. 2019Harnessing Evolution for Multi-Hunk Program Repaircited by 12
  22. 2017Ultra-Large Repair Search Space with Automatically Mined Templates: the Cardumen Mode of Astorcited by 9
  23. 2016An Analysis of the Search Spaces for Generate and Validate Patch Generation Systemscited by 8
  24. 2018Code Vectors: Understanding Programs Through Embedded Abstracted Symbolic Tracescited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 8; 2023: 22; 2024: 26; 2025: 14; 2026: 9.

85 papers.

Sort:

By area:

  1. 2024A Survey on Large Language Models for Code Generationcited by 646
  2. 2021Asleep at the Keyboard? Assessing the Security of GitHub Copilot's Code Contributionscited by 417
  3. 2024Agentless: Demystifying LLM-based Software Engineering Agentscited by 400
  4. 2023Keep the Conversation Going: Fixing 162 out of 337 bugs for 0.42 each using ChatGPTcited by 125
  5. 2021Examining Zero-Shot Vulnerability Repair with Large Language Modelscited by 105
  6. 2024CodeR: Issue Resolving with Multi-Agent and Task Graphscited by 89
  7. 2023Copiloting the Copilots: Fusing Large Language Models with Completion Engines for Automated Program Repaircited by 55
  8. 2023How Effective Are Neural Networks for Fixing Security Vulnerabilitiescited by 50
  9. 2023RepairLLaMA: Efficient Representations and Fine-Tuned Adapters for Program Repaircited by 50
  10. 2021Multilingual training for Software Engineeringcited by 43
  11. 2023RAP-Gen: Retrieval-Augmented Patch Generation with CodeT5 for Automatic Program Repaircited by 43
  12. 2023A New Era in Software Security: Towards Self-Healing Software via Large Language Models and Formal Verificationcited by 42
38 more
  1. 2023Conversational Automated Program Repaircited by 41
  2. 2024UniDebugger: Hierarchical Multi-Agent Framework for Unified Software Debuggingcited by 35
  3. 2024Automatic Programming: Large Language Models and Beyondcited by 35
  4. 2023Natural Language Generation and Understanding of Big Code for AI-Assisted Programming: A Reviewcited by 32
  5. 2023Better patching using LLM prompting, via Self-Consistencycited by 29
  6. 2021On Multi-Modal Learning of Editing Source Codecited by 25
  7. 2021A Survey on Machine Learning Techniques for Source Code Analysiscited by 23
  8. 2023Deep Learning for Code Intelligence: Survey, Benchmark and Toolkitcited by 22
  9. 2025PatchPilot: A Cost-Efficient Software Engineering Agent with Early Attempts on Formal Verificationcited by 22
  10. 2023Towards Efficient Fine-tuning of Pre-trained Code Models: An Experimental Study and Beyondcited by 20
  11. 2024Rectifier: Code Translation with Corrector via LLMscited by 20
  12. 2023ITER: Iterative Neural Repair for Multi-Location Patchescited by 16
  13. 2024RePair: Automated Program Repair with Process-based Feedbackcited by 16
  14. 2025Large Language Models (LLMs) for Source Code Analysis: applications, models and datasetscited by 15
  15. 2023Towards Generating Functionally Correct Code Edits from Natural Language Issue Descriptionscited by 14
  16. 2024Do Large Code Models Understand Programming Concepts? Counterfactual Analysis for Code Predicatescited by 14
  17. 2023KNOD: Domain Knowledge Distilled Tree Decoder for Automated Program Repaircited by 13
  18. 2024Aligning the Objective of LLM-based Program Repaircited by 12
  19. 2022Improving Automated Program Repair with Domain Adaptationcited by 10
  20. 2023RunBugRun -- An Executable Dataset for Automated Program Repaircited by 10
  21. 2022Detect-Localize-Repair: A Unified Framework for Learning to Debug with CodeT5cited by 9
  22. 2024PeaTMOSS: A Dataset and Initial Analysis of Pre-Trained Models in Open-Source Softwarecited by 9
  23. 2026SGAgent: Suggestion-Guided LLM-Based Multi-Agent Framework for Repository-Level Software Repaircited by 9
  24. 2022Poison Attack and Defense on Deep Source Code Processing Modelscited by 8
  25. 2023Automating Code-Related Tasks Through Transformers: The Impact of Pre-trainingcited by 8
  26. 2025Dissecting the SWE-Bench Leaderboards: Profiling Submitters and Architectures of LLM- and Agent-Based Repair Systemscited by 8
  27. 2022Is this Change the Answer to that Problem? Correlating Descriptions of Bug and Code Changes for Evaluating Patch Correctnesscited by 7
  28. 2023Revisiting the Plastic Surgery Hypothesis via Large Language Modelscited by 7
  29. 2024Automated Program Repair: Emerging trends pose and expose problems for benchmarkscited by 7
  30. 2023Frustrated with Code Quality Issues? LLMs can Help!cited by 5
  31. 2023Out of Context: How important is Local Context in Neural Program Repair?cited by 5
  32. 2024Towards Reliable Evaluation of Neural Program Repair with Natural Robustness Testingcited by 5
  33. 2024Dynamic Intelligence Assessment: Benchmarking LLMs on the Road to AGI with a Focus on Model Confidencecited by 5
  34. 2024Memory-Efficient Large Language Models for Program Repair with Semantic-Guided Patch Generationcited by 5
  35. 2021Predicting Patch Correctness Based on the Similarity of Failing Test Casescited by 4
  36. 2024Translating between SQL Dialects for Cloud Migrationcited by 4
  37. 2024Open-Source AI-based SE Tools: Opportunities and Challenges of Collaborative Software Learningcited by 4
  38. 2024Leveraging Reviewer Experience in Code Review Comment Generationcited by 4

50 most cited of 85 All 85 (JSON)