mlsanityData to 14 Oct 2026

Knowledge Transfer from High-Resource to Low-Resource Programming Languages for Code LLMs

arXiv 2308.09895 ↗First posted 19 Aug 2023cs.PL cs.LGcited by 45

Not on the map. Why?

Abstract (arXiv)

Over the past few years, Large Language Models of Code (Code LLMs) have started to have a significant impact on programming practice. Code LLMs are also emerging as building blocks for research in programming languages and software engineering. However, Code LLMs produce impressive results on programming languages that are well represented in their training data (e.g., Java, Python, or JavaScript), but struggle with low-resource languages that have limited training data available. Low resource languages include OCaml, Racket, and several others. This paper presents an effective approach for boosting the performance of Code LLMs on low-resource languages using semi-synthetic data. Our approach, MultiPL-T, translates training data from high-resource languages into training data for low-resource languages in the following way. 1) We use a Code LLM to synthesize tests for commented code from a high-resource language, filtering out faulty tests and code with low test coverage. 2) We use a Code LLM to translate Python code to a target low-resource language, and use tests to validate the translation. We apply this approach to generate tens of thousands of validated training items for Julia, Lua, OCaml, R, and Racket. Furthermore, we use an open model (StarCoderBase) with open training data (The Stack), which allows us to decontaminate benchmarks, train models without violating licenses, and run experiments that could not otherwise be done. With MultiPL-T generated data, we present fine-tuned versions of StarCoderBase and Code Llama for Julia, Lua, OCaml, R, and Racket. On established benchmarks (MultiPL-E), these models outperform other open Code LLMs. The MultiPL-T approach is easy to apply to new languages, and is significantly more efficient and effective than alternatives such as training longer.

Key facts. Cited by 45 papers in the map (data through 14 Oct 2026). Builds on 36 of its 93 references that are in the map. First posted on arXiv 19 Aug 2023.

Builds on

36 of 93 references.

References · 36

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2022Training language models to follow instructions with human feedbackcited by 15,971
  3. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  4. 2021Program Synthesis with Large Language Modelscited by 3,637
  5. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,724
  6. 2019ZeRO: Memory Optimizations Toward Training Trillion Parameter Modelscited by 1,301
  7. 2023PaLM 2 Technical Reportcited by 1,162
  8. 2023StarCoder: may the source be with you!cited by 799
  9. 2023WizardCoder: Empowering Code Large Language Models with Evol-Instructcited by 733
  10. 2021Deduplicating Training Data Makes Language Models Bettercited by 714
  11. 2023Textbooks Are All You Needcited by 569
  12. 2022DS-1000: A Natural and Reliable Benchmark for Data Science Code Generationcited by 452
24 more
  1. 2022A Systematic Evaluation of Large Language Models of Codecited by 363
  2. 2022The Stack: 3 TB of permissively licensed source codecited by 359
  3. 2023CodeGeeX: A Pre-Trained Model for Code Generation with Multilingual Benchmarking on HumanEval-Xcited by 300
  4. 2023Using an LLM to Help With Code Understandingcited by 228
  5. 2023OctoPack: Instruction Tuning Code Large Language Modelscited by 189
  6. 2023SantaCoder: don't reach for the stars!cited by 170
  7. 2022Multi-lingual Evaluation of Code Generation Modelscited by 159
  8. 2023CodeGen2: Lessons for Training LLMs on Programming and Natural Languagescited by 125
  9. 2023Baldur: Whole-Proof Generation and Repair with Large Language Modelscited by 119
  10. 2022Productivity Assessment of Neural Code Completioncited by 98
  11. 2023The Programmer's Assistant: Conversational Interaction with a Large Language Model for Software Developmentcited by 96
  12. 2023Fuzz4All: Universal Fuzzing with Large Language Modelscited by 88
  13. 2021Leveraging Automated Unit Tests for Unsupervised Code Translationcited by 82
  14. 2022Repair Is Nearly Generation: Multilingual Program Repair with LLMscited by 68
  15. 2021Multilingual training for Software Engineeringcited by 43
  16. 2022Code Generation Tools (Almost) for Free? A Study of Few-Shot, Pre-Trained Language Models on Codecited by 39
  17. 2023Generating High-Precision Feedback for Programming Syntax Errors using Large Language Modelscited by 34
  18. 2023Measuring The Impact Of Programming Language Distributioncited by 32
  19. 2023StudentEval: A Benchmark of Student-Written Prompts for Large Language Models of Codecited by 32
  20. 2022On the Transferability of Pre-trained Language Models for Low-Resource Programming Languagescited by 30
  21. 2016Understanding the Factors that Impact the Popularity of GitHub Repositoriescited by 27
  22. 2020Automated Unit Test Generation for Pythoncited by 18
  23. 2023Data Race Detection Using Large Language Modelscited by 11
  24. 2023Type Prediction With Program Decomposition and Fill-in-the-Type Trainingcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 16; 2025: 13; 2026: 13.

45 papers.

Sort:

By area:

  1. 2024Formal Mathematical Reasoning: A New Frontier in AIcited by 81
  2. 2024A Survey on LLM-based Code Generation for Low-Resource and Domain-Specific Programming Languagescited by 66
  3. 2023Unifying the Perspectives of NLP and Software Engineering: A Survey on Language Models for Codecited by 62
  4. 2024SelfCodeAlign: Self-Alignment for Code Generationcited by 62
  5. 2025Synthetic Data Generation Using Large Language Models: Advances in Text and Codecited by 61
  6. 2023Can It Edit? Evaluating the Ability of Large Language Models to Follow Code Editing Instructionscited by 48
  7. 2025Speed at the Cost of Quality: How Cursor AI Increases Short-Term Velocity and Long-Term Complexity in Open-Source Projectscited by 24
  8. 2024Syzygy: Dual Code-Test C to (safe) Rust Translation using LLMs and Dynamic Analysiscited by 16
  9. 2024PROC2PDDL: Open-Domain Planning Representations from Textscited by 15
  10. 2024Statically Contextualizing Large Language Models with Typed Holescited by 9
  11. 2024MoDEM: Mixture of Domain Expert Modelscited by 9
  12. 2024HPC-Coder-V2: Studying Code LLMs Across Low-Resource Parallel Languagescited by 8
33 more
  1. 2024Synthetic Programming Elicitation for Text-to-Code in Very Low-Resource Programming and Formal Languagescited by 6
  2. 2023Cross-lingual Transfer in Programming Languages: An Extensive Empirical Studycited by 5
  3. 2025Adaptive LoRA Merge with Parameter Pruning for Low-Resource Generationcited by 5
  4. 2025Agnostics: Learning to Code in Any Programming Language via Reinforcement with a Universal Learning Environmentcited by 5
  5. 2025AgentPack: A Dataset of Code Changes, Co-Authored by Agents and Humanscited by 5
  6. 2024Do Current Language Models Support Code Intelligence for R Programming Language?cited by 4
  7. 2025More Than a Score: Probing the Impact of Prompt Specificity on LLM Code Generationcited by 4
  8. 2024Evaluating Quantized Large Language Models for Code Generation on Low-Resource Language Benchmarkscited by 3
  9. 2024Bridge-Coder: Unlocking LLMs' Potential to Overcome Language Gaps in Low-Resource Codecited by 3
  10. 2024Mastering the Craft of Data Synthesis for CodeLLMscited by 3
  11. 2025Program Skeletons for Automated Program Translationcited by 3
  12. 2025Unifying Inference-Time Planning Language Generationcited by 3
  13. 2025Across Programming Language Silos: A Study on Cross-Lingual Retrieval-augmented Code Generationcited by 3
  14. 2024LLMsAgainstHate @ NLU of Devanagari Script Languages 2025: Hate Speech Detection and Target Identification in Devanagari Languages via Parameter Efficient Fine-Tuning of LLMscited by 2
  15. 2025Building A Proof-Oriented Programmer That Is 64% Better Than GPT-4o Under Data Scarcitycited by 2
  16. 2025Beyond Language Barriers: Multi-Agent Coordination for Multi-Language Code Generationcited by 2
  17. 2025Do Not Merge My Model! Safeguarding Open-Source LLMs Against Unauthorized Model Mergingcited by 2
  18. 2026Parallel-SFT: Improving Zero-Shot Cross-Programming-Language Transfer for Code RLcited by 2
  19. 2026InstructDiff: Domain-Adaptive Data Selection via Differential Entropy for Efficient LLM Fine-Tuningcited by 1
  20. 2026Bridging the Knowledge Void: Inference-time Acquisition of Unfamiliar Programming Languages for Coding Taskscited by 1
  21. 2026CodePivot: Bootstrapping Multilingual Transpilation in LLMs via Reinforcement Learning without Parallel Corporacited by 1
  22. 2026Syntax Without Semantics: Teaching Large Language Models to Code in an Unseen Languagecited by 1
  23. 2026Formal Disco: Scalable Open-Ended Generation of Formally Verified Programscited by 1
  24. 2024Investigating the Transferability of Code Repair for Low-Resource Programming Languagescited by 0
  25. 2024SimpleStrat: Diversifying Language Model Generation with Stratificationcited by 0
  26. 2025SoK: Understanding (New) Security Issues Across AI4Code Use Casescited by 0
  27. 2026The New Compiler Stack: A Survey on the Synergy of LLMs and Compilerscited by 0
  28. 2026BhashaSetu: Cross-Lingual Knowledge Transfer from High-Resource to Extreme Low-Resource Languagescited by 0
  29. 2026Compiler-Guided Inference-Time Adaptation: Improving GPT-5 Programming Performance in Idriscited by 0
  30. 2026ROSUM-MCTS: Monte Carlo Tree Search-Inspired HDL Code Summarization with Structural Rewardscited by 0
  31. 2026Decode-Time Grammars: Constrained LLM Generation over a Refinement Order of Grammar Fragmentscited by 0
  32. 2026BC-Bench: Evaluating Agentic Engineering in a Domain-Specific Language for ERPcited by 0
  33. 2026LLM-Based FORM Code Generation with Verification-Driven Fine-Tuningcited by 0