mlsanityData to 7 Oct 2026

Leveraging Automated Unit Tests for Unsupervised Code Translation

arXiv 2110.06773 ↗First posted 13 Oct 2021cs.SE cs.CL cs.LGcited by 82

Not on the map. Why?

Abstract (arXiv)

With little to no parallel data available for programming languages, unsupervised methods are well-suited to source code translation. However, the majority of unsupervised machine translation approaches rely on back-translation, a method developed in the context of natural language translation and one that inherently involves training on noisy inputs. Unfortunately, source code is highly sensitive to small changes; a single token can result in compilation failures or erroneous programs, unlike natural languages where small inaccuracies may not change the meaning of a sentence. To address this issue, we propose to leverage an automated unit-testing system to filter out invalid translations, thereby creating a fully tested parallel corpus. We found that fine-tuning an unsupervised model with this filtered data set significantly reduces the noise in the translations so-generated, comfortably outperforming the state-of-the-art for all language pairs studied. In particular, for Java → Python and Python → C++ we outperform the best previous methods by more than 16% and 24% respectively, reducing the error rate by more than 35%.

Key facts. Cited by 82 papers in the map (data through 7 Oct 2026). Builds on 35 of its 62 references that are in the map. First posted on arXiv 13 Oct 2021.

Builds on

35 of 62 references.

References · 35

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  4. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  5. 2021Program Synthesis with Large Language Modelscited by 3,509
  6. 2020CodeBERT: A Pre-Trained Model for Programming and Natural Languagescited by 1,286
  7. 2021Measuring Coding Challenge Competence With APPScited by 879
  8. 2015Improving Neural Machine Translation Models with Monolingual Datacited by 784
  9. 2021CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generationcited by 732
  10. 2020GraphCodeBERT: Pre-training Code Representations with Data Flowcited by 600
  11. 2021Unified Pre-training for Program Understanding and Generationcited by 361
  12. 2017Synthetic and Natural Noise Both Break Neural Machine Translationcited by 304
23 more
  1. 2020Unsupervised Translation of Programming Languagescited by 262
  2. 2017Learning to Represent Programs with Graphscited by 219
  3. 2019Machine Learning Testing: Survey, Landscapes and Horizonscited by 213
  4. 2019SPoC: Search-based Pseudocode to Codecited by 176
  5. 2018SequenceR: Sequence-to-Sequence Learning for End-to-End Program Repaircited by 144
  6. 2018Phrase-Based & Neural Unsupervised Machine Translationcited by 138
  7. 2020Unit Test Case Generation with Transformers and Focal Contextcited by 118
  8. 2018An Empirical Study on Learning Bug-Fixing Patches in the Wild via Neural Machine Translationcited by 106
  9. 2018Tree-to-tree Neural Networks for Program Translationcited by 93
  10. 2020Graph-based, Self-Supervised Program Repair from Diagnostic Feedbackcited by 93
  11. 2018On the Impact of Various Types of Noise on Neural Machine Translationcited by 76
  12. 2020Code Prediction by Feeding Trees to Transformerscited by 70
  13. 2021DOBF: A Deobfuscation Pre-Training Objective for Programming Languagescited by 68
  14. 2017A parallel corpus of Python functions and documentation strings for automated code documentation and code generationcited by 56
  15. 2020SlimIPL: Language-Model-Free Iterative Pseudo-Labelingcited by 54
  16. 2017Code Completion with Neural Attention and Pointer Networkscited by 49
  17. 2020Fast and Memory-Efficient Neural Code Completioncited by 38
  18. 2019Learning to Fix Build Errors with Graph2Diff Neural Networkscited by 26
  19. 2017Dynamic Neural Program Embedding for Program Repaircited by 23
  20. 2019A Self-Attentional Neural Architecture for Code Completion with Multi-Task Learningcited by 18
  21. 2021DeepDebug: Fixing Python Bugs Using Stack Traces, Backtranslation, and Code Skeletonscited by 17
  22. 2020Industry-scale IR-based Bug Localization: A Perspective from Facebookcited by 5
  23. 2016Leveraging Parallel Data Processing Frameworks with Verified Liftingcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 7; 2023: 22; 2024: 18; 2025: 23; 2026: 12.

82 papers.

Sort:

By area:

  1. 2023Code Llama: Open Foundation Models for Codecited by 2,105
  2. 2023Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generationcited by 1,332
  3. 2023Teaching Large Language Models to Self-Debugcited by 963
  4. 2024Agentless: Demystifying LLM-based Software Engineering Agentscited by 400
  5. 2022CodeT: Code Generation with Generated Testscited by 369
  6. 2023Planning with Large Language Models for Code Generationcited by 179
  7. 2022Language Models Can Teach Themselves to Program Bettercited by 75
  8. 2024Exploring and Unleashing the Power of Large Language Models in Automated Code Translationcited by 57
  9. 2023CodeTransOcean: A Comprehensive Multilingual Benchmark for Code Translationcited by 55
  10. 2023xCodeEval: A Large Scale Multilingual Multitask Benchmark for Code Understanding, Generation, Translation and Retrievalcited by 46
  11. 2023Knowledge Transfer from High-Resource to Low-Resource Programming Languages for Code LLMscited by 45
  12. 2022Code Translation with Compiler Representationscited by 42
38 more
  1. 2025CodeCoR: An LLM-Based Self-Reflective Multi-Agent Framework for Code Generationcited by 33
  2. 2024CRUXEval-X: A Benchmark for Multilingual Code Reasoning, Understanding and Executioncited by 31
  3. 2025VERINA: Benchmarking Verifiable Code Generationcited by 30
  4. 2024AlphaTrans: A Neuro-Symbolic Compositional Approach for Repository-Level Code Translation and Validationcited by 28
  5. 2023Deep Learning for Code Intelligence: Survey, Benchmark and Toolkitcited by 22
  6. 2023CoTran: An LLM-based Code Translator using Reinforcement Learning with Feedback from Compiler and Symbolic Executioncited by 21
  7. 2024IRCoder: Intermediate Representations Make Language Models Robust Multilingual Code Generatorscited by 21
  8. 2024Rectifier: Code Translation with Corrector via LLMscited by 20
  9. 2023Trustworthy and Synergistic Artificial Intelligence for Software Engineering: Vision and Roadmapscited by 19
  10. 2024NaturalCodeBench: Examining Coding Performance Mismatch on HumanEval and Natural User Promptscited by 19
  11. 2024CodeRosetta: Pushing the Boundaries of Unsupervised Code Translation for Parallel Programmingcited by 19
  12. 2024Text Generation: A Systematic Literature Review of Tasks, Evaluation, and Challengescited by 18
  13. 2024LangProp: A code optimization framework using Large Language Models applied to drivingcited by 17
  14. 2023Exploring the Robustness of Large Language Models for Solving Programming Problemscited by 16
  15. 2024InterTrans: Leveraging Transitive Intermediate Translations to Enhance LLM-based Code Translationcited by 15
  16. 2025CSR-Bench: Benchmarking LLM Agents in Deployment of Computer Science Research Repositoriescited by 15
  17. 2025From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligencecited by 13
  18. 2023Explain-then-Translate: An Analysis on Improving Program Translation with Self-generated Explanationscited by 12
  19. 2025Enhancing LLM Performance Through Debate: An Empirical Study on Multi-Agent Debate for Coding Taskscited by 11
  20. 2023Program Translation via Code Distillationcited by 10
  21. 2023Multilingual Code Co-Evolution Using Large Language Modelscited by 9
  22. 2023Data Augmentation for Code Translation with Comparable Corpora and Multiple Referencescited by 9
  23. 2024Output Format Biases in the Evaluation of Large Language Models for Code Translationcited by 9
  24. 2024B4: Towards Optimal Assessment of Plausible Code Solutions with Plausible Testscited by 9
  25. 2026LLMs Corrupt Your Documents When You Delegatecited by 9
  26. 2022Benchmarking Language Models for Code Syntax Understandingcited by 8
  27. 2023Syntax and Domain Aware Model for Unsupervised Program Translationcited by 7
  28. 2024TransAgent: Enhancing LLM-Based Code Translation via Fine-Grained Execution Alignmentcited by 7
  29. 2022A Theory of Unsupervised Translation Motivated by Understanding Animal Communicationcited by 6
  30. 2023Validating Multimedia Content Moderation Software via Semantic Fusioncited by 5
  31. 2025Agnostics: Learning to Code in Any Programming Language via Reinforcement with a Universal Learning Environmentcited by 5
  32. 2025EffiReasonTrans: RL-Optimized Reasoning for Code Translationcited by 5
  33. 2026RepoRepair: Leveraging Code Documentation for Repository-Level Automated Program Repaircited by 5
  34. 2023Configuration Validation with Large Language Modelscited by 4
  35. 2024A Joint Learning Model with Variational Interaction for Multilingual Program Translationcited by 4
  36. 2024Fortran2CPP: Automating Fortran-to-C++ Translation using LLMs via Multi-Turn Dialogue and Dual-Agent Integrationcited by 4
  37. 2025Automated Testing of COBOL to Java Transformationcited by 4
  38. 2025Function-to-Style Guidance of LLMs for Code Translationcited by 4

50 most cited of 82 All 82 (JSON)