Published in Artificial Intelligence in Education, 2023
In this paper, I introduce a simple strategy to instantiate language models for repairing student programs. The strategy consists in finetuning existing open models, such as those available on HuggingFace, using as ground truth the repairs found by Automated Repair Tools.
Recommended citation: Koutcheme, C. (2023). Training Language Models for Programming Feedback Using Automated Repair Tools. In Artificial Intelligence in Education: 24th International Conference, AIED 2023, Tokyo, Japan, July 3–7, 2023 https://link.springer.com/chapter/10.1007/978-3-031-36272-9_79