Towards Pedagogical LLMs with Supervised Fine Tuning for Computing Education
This addresses concerns that LLMs may hinder learning outcomes in computing education, though it appears incremental.
This paper tackles the problem of improving large language models' pedagogical alignment in computing education by supervised fine-tuning on a dataset of 2,500 question/answer pairs from programming course forums, finding initial benefits in alignment with educational principles.
This paper investigates supervised fine-tuning of large language models (LLMs) to improve their pedagogical alignment in computing education, addressing concerns that LLMs may hinder learning outcomes. The project utilised a proprietary dataset of 2,500 high quality question/answer pairs from programming course forums, and explores two research questions: the suitability of university course forums in contributing to fine-tuning datasets, and how supervised fine-tuning can improve LLMs' alignment with educational principles such as constructivism. Initial findings suggest benefits in pedagogical alignment of LLMs, with deeper evaluations required.