Recent breakthroughs in Large Language Models (LLMs), such as GPT-3 and Codex, now enable software developers to generate code based on a natural language prompt. Within computer science education, researchers are exploring the potential for LLMs to generate code explanations and programming assignments using carefully crafted prompts. These advances may enable students to interact with code in new ways while helping instructors scale their learning materials. However, LLMs also introduce new implications for academic integrity, curriculum design, and software engineering careers. This workshop will demonstrate the capabilities of LLMs to help attendees evaluate whether and how LLMs might be integrated into their pedagogy and research. We will also engage attendees in brainstorming to consider how LLMs will impact our field.
@article{arxiv.2212.05113,
title = {Automatically Generating CS Learning Materials with Large Language Models},
author = {Stephen MacNeil and Andrew Tran and Juho Leinonen and Paul Denny and Joanne Kim and Arto Hellas and Seth Bernstein and Sami Sarsa},
journal= {arXiv preprint arXiv:2212.05113},
year = {2022}
}
Comments
In Proceedings of the 54th ACM Technical Symposium on Computing Science Education