Towards Pedagogical LLMs with Supervised Fine Tuning for Computing Education
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910682572652544 |
|---|---|
| author | Vassar, Alexandra Renzella, Jake Ross, Emily Taylor, Andrew |
| author_facet | Vassar, Alexandra Renzella, Jake Ross, Emily Taylor, Andrew |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_01765 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Towards Pedagogical LLMs with Supervised Fine Tuning for Computing Education Vassar, Alexandra Renzella, Jake Ross, Emily Taylor, Andrew Computation and Language 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. |
| title | Towards Pedagogical LLMs with Supervised Fine Tuning for Computing Education |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2411.01765 |