mlsanityData to 14 Oct 2026

Multilingual Code Co-Evolution Using Large Language Models

arXiv 2307.14991 ↗First posted 27 Jul 2023cs.SE cs.AIcited by 9

Not on the map. Why?

Abstract (arXiv)

Many software projects implement APIs and algorithms in multiple programming languages. Maintaining such projects is tiresome, as developers have to ensure that any change (e.g., a bug fix or a new feature) is being propagated, timely and without errors, to implementations in other programming languages. In the world of ever-changing software, using rule-based translation tools (i.e., transpilers) or machine learning models for translating code from one language to another provides limited value. Translating each time the entire codebase from one language to another is not the way developers work. In this paper, we target a novel task: translating code changes from one programming language to another using large language models (LLMs). We design and implement the first LLM, dubbed Codeditor, to tackle this task. Codeditor explicitly models code changes as edit sequences and learns to correlate changes across programming languages. To evaluate Codeditor, we collect a corpus of 6,613 aligned code changes from 8 pairs of open-source software projects implementing similar functionalities in two programming languages (Java and C#). Results show that Codeditor outperforms the state-of-the-art approaches by a large margin on all commonly used automatic metrics. Our work also reveals that Codeditor is complementary to the existing generation-based models, and their combination ensures even greater performance.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 33 of its 66 references that are in the map. First posted on arXiv 27 Jul 2023.

Builds on

33 of 66 references.

References · 33

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,673
  4. 2021Program Synthesis with Large Language Modelscited by 3,637
  5. 2020Longformer: The Long-Document Transformercited by 3,413
  6. 2021CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generationcited by 906
  7. 2021CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generationcited by 744
  8. 2020CodeBLEU: a Method for Automatic Evaluation of Code Synthesiscited by 479
  9. 2021Unified Pre-training for Program Understanding and Generationcited by 366
  10. 2022UniXcoder: Unified Cross-Modal Pre-training for Code Representationcited by 361
  11. 2023CodeT5+: Open Code Large Language Models for Code Understanding and Generationcited by 333
  12. 2020Unsupervised Translation of Programming Languagescited by 263
21 more
  1. 2022Few-shot training LLMs for project-specific code-summarizationcited by 129
  2. 2023Unlimiformer: Long-Range Transformers with Unlimited Length Inputcited by 128
  3. 2022Automating Code Review Activities by Large-Scale Pre-trainingcited by 98
  4. 2018Tree-to-tree Neural Networks for Program Translationcited by 93
  5. 2021Leveraging Automated Unit Tests for Unsupervised Code Translationcited by 82
  6. 2022Using Pre-Trained Models to Boost Code Review Automationcited by 63
  7. 2020Seq2Edits: Sequence Transduction Using Span-level Edit Operationscited by 58
  8. 2019On Learning Meaningful Code Changes via Neural Machine Translationcited by 50
  9. 2022CoditT5: Pretraining for Source Code and Natural Language Editingcited by 45
  10. 2018CODIT: Code Editing with Tree-Based Neural Modelscited by 40
  11. 2022Automatic Code Documentation Generation Using GPT-3cited by 37
  12. 2022StructCoder: Structure-Aware Transformer for Code Generationcited by 34
  13. 2020Learning to Update Natural Language Comments Based on Code Changescited by 31
  14. 2021On Multi-Modal Learning of Editing Source Codecited by 25
  15. 2020Patching as Translation: the Data and the Metaphorcited by 18
  16. 2021Learning Structural Edits via Incremental Tree Transformationscited by 16
  17. 2021Impact of Evaluation Methodologies on Code Summarizationcited by 11
  18. 2022Automated Transpilation of Imperative to Functional Code using Neural-Guided Program Synthesis (Extended Version)cited by 7
  19. 2021Automating the Removal of Obsolete TODO Commentscited by 6
  20. 2018Hierarchical Learning of Cross-Language Mappings through Distributed Vector Representations for Codecited by 5
  21. 2022Using Large-scale Heterogeneous Graph Representation Learning for Code Review Recommendations at Microsoftcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 5; 2025: 2; 2026: 1.

9 papers.

  1. 2023Large Language Models for Software Engineering: A Systematic Literature Reviewcited by 399
  2. 2024LLMs: A Game-Changer for Software Engineers?cited by 11
  3. 2024RAMBO: Enhancing RAG-based Repository-Level Method Body Completioncited by 10
  4. 2024Understanding Defects in Generated Codes by Language Modelscited by 5
  5. 2024exLong: Generating Exceptional Behavior Tests with Large Language Modelscited by 4
  6. 2024Promise and Peril of Collaborative Code Generation Models: Balancing Effectiveness and Memorizationcited by 4
  7. 2025Benchmarking AI Models in Software Engineering: A Review, Search Tool, and Unified Approach for Elevating Benchmark Qualitycited by 4
  8. 2025Mix-of-Language-Experts Architecture for Multilingual Programmingcited by 3
  9. 2026Multimodal QUD: Inquisitive Questions from Scientific Figurescited by 0