mlsanityData to 7 Oct 2026

Investigating the Transferability of Code Repair for Low-Resource Programming Languages

arXiv 2406.14867 ↗First posted 21 Jun 2024cs.LG cs.AI cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Large language models (LLMs) have shown remarkable performance on code generation tasks. A recent use case is iterative code repair, where an LLM fixes an incorrect program by rationalizing about errors and generating new code. Recent works augment the code repair process by integrating modern techniques such as chain-of-thought reasoning or distillation, but only study their benefits on high-resource languages like Python, and ignore low-resource languages like Perl. To address this gap of knowledge, we investigate the benefits of distilling code repair for both high and low resource languages to determine if the techniques that are effective in a high resource setting are also applicable in a low resource setting. Our evaluation shows that distilling the ability to repair code has language dependent benefits. To explain this behavior, we perform a further analysis and find that contrary to preexisting beliefs, the correlation between reasoning ability and code correction ability is weak. We hypothesize this weak correlation is magnified in low-resource settings where base models lack deep knowledge of a programming language, leading to wavering benefits of code repair.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 29 of its 38 references that are in the map. First posted on arXiv 21 Jun 2024.

Builds on

29 of 38 references.

References · 29

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  4. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  5. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  6. 2023Code Llama: Open Foundation Models for Codecited by 2,105
  7. 2024DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligencecited by 1,154
  8. 2023WizardLM: Empowering large pre-trained language models to follow complex instructionscited by 1,116
  9. 2023Teaching Large Language Models to Self-Debugcited by 963
  10. 2021Measuring Coding Challenge Competence With APPScited by 879
  11. 2023WizardCoder: Empowering Code Large Language Models with Evol-Instructcited by 728
  12. 2023Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategiescited by 236
17 more
  1. 2024When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMscited by 230
  2. 2023Is Self-Repair a Silver Bullet for Code Generation?cited by 191
  3. 2022Multi-lingual Evaluation of Code Generation Modelscited by 158
  4. 2022MultiPL-E: A Scalable and Extensible Approach to Benchmarking Neural Code Generationcited by 132
  5. 2022Explanations from Large Language Models Make Small Reasoners Bettercited by 123
  6. 2023Self-Edit: Fault-Aware Code Editor for Code Generationcited by 110
  7. 2023Improving Code Generation by Training with Natural Language Feedbackcited by 75
  8. 2024LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancementcited by 69
  9. 2023CodeChain: Towards Modular Code Generation Through Chain of Self-revisions with Representative Sub-modulescited by 58
  10. 2023Knowledge Transfer from High-Resource to Low-Resource Programming Languages for Code LLMscited by 45
  11. 2024CYCLE: Learning to Self-Refine the Code Generationcited by 39
  12. 2023Measuring The Impact Of Programming Language Distributioncited by 32
  13. 2024Enhancing Code Generation Performance of Smaller Models by Distilling the Reasoning Ability of LLMscited by 17
  14. 2024ReflectionCoder: Learning from Reflection Sequence for Enhanced One-off Code Generationcited by 14
  15. 2023Personalised Distillation: Empowering Open-Sourced LLMs with Adaptive Learning for Code Generationcited by 7
  16. 2022MultiCoder: Multi-Programming-Lingual Pre-Training for Low-Resource Code Completioncited by 6
  17. 2023Cross-lingual Transfer in Programming Languages: An Extensive Empirical Studycited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Optimizing Token Consumption in LLMs: A Nano Surge Approach for Code Reasoning Efficiency
  2. 2025FeedbackEval: A Benchmark for Evaluating Large Language Models in Feedback-Driven Code Repair Tasks
  3. 2025Unlocking LLM Repair Capabilities Through Cross-Language Translation and Multi-Agent Refinement
  4. 2025Towards Effectively Leveraging Execution Traces for Program Repair with Code LLMs
  5. 2024MORepair: Teaching LLMs to Repair Code via Multi-Objective Fine-tuning
  6. 2024Code Repair with LLMs gives an Exploration-Exploitation Tradeoff
  7. 2024RePair: Automated Program Repair with Process-based Feedback
  8. 2025T3: Multi-level Tree-based Automatic Program Repair with Large Language Models