mlsanityData to 7 Oct 2026

Unsupervised Translation of Programming Languages

arXiv 2006.03511 ↗First posted 5 Jun 2020cs.CL cs.PLcited by 262

Not on the map. Why?

Cited by 21 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

A transcompiler, also known as source-to-source translator, is a system that converts source code from a high-level programming language (such as C++ or Python) to another. Transcompilers are primarily used for interoperability, and to port codebases written in an obsolete or deprecated language (e.g. COBOL, Python 2) to a modern one. They typically rely on handcrafted rewrite rules, applied to the source code abstract syntax tree. Unfortunately, the resulting translations often lack readability, fail to respect the target language conventions, and require manual modifications in order to work properly. The overall translation process is timeconsuming and requires expertise in both the source and target languages, making code-translation projects expensive. Although neural models significantly outperform their rule-based counterparts in the context of natural language translation, their applications to transcompilation have been limited due to the scarcity of parallel data in this domain. In this paper, we propose to leverage recent approaches in unsupervised machine translation to train a fully unsupervised neural transcompiler. We train our model on source code from open source GitHub projects, and show that it can translate functions between C++, Java, and Python with high accuracy. Our method relies exclusively on monolingual source code, requires no expertise in the source or target languages, and can easily be generalized to other programming languages. We also build and release a test set composed of 852 parallel functions, along with unit tests to check the correctness of translations. We show that our model outperforms rule-based commercial baselines by a significant margin.

Key facts. Cited by 262 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 35; 2022: 31; 2023: 61; 2024: 53; 2025: 52; 2026: 30.

262 papers.

Sort:

By area:

  1. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  2. 2021Program Synthesis with Large Language Modelscited by 3,509
  3. 2023Code Llama: Open Foundation Models for Codecited by 2,105
  4. 2023Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generationcited by 1,332
  5. 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,302
  6. 2023Teaching Large Language Models to Self-Debugcited by 963
  7. 2021CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generationcited by 890
  8. 2021Measuring Coding Challenge Competence With APPScited by 879
  9. 2021CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generationcited by 732
  10. 2024A Survey on Large Language Models for Code Generationcited by 646
  11. 2024Agentless: Demystifying LLM-based Software Engineering Agentscited by 400
  12. 2021Unified Pre-training for Program Understanding and Generationcited by 361
38 more
  1. 2024CRUXEval: A Benchmark for Code Reasoning, Understanding and Executioncited by 294
  2. 2021Unsolved Problems in ML Safetycited by 291
  3. 2021CodeNet: A Large-Scale AI for Code Dataset for Learning a Diversity of Coding Taskscited by 199
  4. 2022HyperTree Proof Search for Neural Theorem Provingcited by 192
  5. 2023Planning with Large Language Models for Code Generationcited by 179
  6. 2022Multi-lingual Evaluation of Code Generation Modelscited by 158
  7. 2024Multi-Step Reasoning with Large Language Models, a Surveycited by 140
  8. 2024Debug like a Human: A Large Language Model Debugger via Verifying Runtime Execution Step-by-stepcited by 123
  9. 2024Beyond Functional Correctness: Exploring Hallucinations in LLM-Generated Codecited by 106
  10. 2023Execution-based Code Generation using Deep Reinforcement Learningcited by 95
  11. 2024RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graphcited by 88
  12. 2022Natural Language to Code Generation in Interactive Data Science Notebookscited by 86
  13. 2021Leveraging Automated Unit Tests for Unsupervised Code Translationcited by 82
  14. 2021Break-It-Fix-It: Unsupervised Learning for Program Repaircited by 71
  15. 2024Reuse, Don't Retrain: A Recipe for Continued Pretraining of Language Modelscited by 69
  16. 2021DOBF: A Deobfuscation Pre-Training Objective for Programming Languagescited by 68
  17. 2024Getting the most out of your tokenizer for pre-training and domain adaptationcited by 65
  18. 2024EffiBench: Benchmarking the Efficiency of Automatically Generated Codecited by 62
  19. 2021CoTexT: Multi-task Learning with Code-Text Transformercited by 61
  20. 2024SelfCodeAlign: Self-Alignment for Code Generationcited by 61
  21. 2021AVATAR: A Parallel Corpus for Java-Python Program Translationcited by 59
  22. 2024Exploring and Unleashing the Power of Large Language Models in Automated Code Translationcited by 57
  23. 2025OpenCodeInstruct: A Large-scale Instruction Tuning Dataset for Code LLMscited by 57
  24. 2023CodeTransOcean: A Comprehensive Multilingual Benchmark for Code Translationcited by 55
  25. 2022XLCoST: A Benchmark Dataset for Cross-lingual Code Intelligencecited by 54
  26. 2021A Survey of Machine Learning for Computer Architecture and Systemscited by 53
  27. 2022NatGen: Generative pre-training by "Naturalizing" source codecited by 53
  28. 2023Bias Testing and Mitigation in LLM-based Code Generationcited by 53
  29. 2023Large Language Models for Compiler Optimizationcited by 52
  30. 2022Investigating Explainability of Generative AI for Code through Scenario-based Designcited by 47
  31. 2022PanGu-Coder: Program Synthesis with Function-Level Language Modelingcited by 47
  32. 2023xCodeEval: A Large Scale Multilingual Multitask Benchmark for Code Understanding, Generation, Translation and Retrievalcited by 46
  33. 2023Large Language Models and Simple, Stupid Bugscited by 45
  34. 2024You Name It, I Run It: An LLM Agent to Execute Tests of Arbitrary Projectscited by 45
  35. 2023SelfEvolve: A Code Evolution Framework via Large Language Modelscited by 43
  36. 2022Code Translation with Compiler Representationscited by 42
  37. 2022No More Fine-Tuning? An Experimental Evaluation of Prompt Tuning in Code Intelligencecited by 41
  38. 2021TreeBERT: A Tree-Based Pre-Trained Model for Programming Languagecited by 40

50 most cited of 262 All 262 (JSON)