Leveraging Open Source LLMs for Software Engineering Education and Training
Generative AI, particularly large language models (LLMs), presents innovative opportunities to enhance software engineering education. Open source LLMs such as LLaMA and Mistral leverage the potential of generative AI offering distinct advantages over proprietary options including transparency, customizability, collaboration, and cost savings. This paper develops a catalog of LLM prompt examples tailored for software engineering teaching, mapped to knowledge areas from the Software Engineering Body of Knowledge (SWEBoK) framework. Example prompts demonstrate LLMs’ capabilities in eliciting requirements, diagram generation, API simulation, effort estimation through role-playing, and other areas. The methodology involves evaluating prompt responses from ChatGPT, Mistral, and LLaMA on representative tasks. Quantitative and qualitative analysis assesses quality, usefulness, and correctness. Findings show ChatGPT and Mistral outperforming LLaMA overall, but no model perfectly executes complex interactions. We examine implications and challenges of integrating open source LLMs into classrooms, emphasizing the need for oversight, verification, and thoughtful prompt design aligned with pedagogical objectives.
Tue 30 JulDisplayed time zone: Amsterdam, Berlin, Bern, Rome, Stockholm, Vienna change
10:30 - 12:00 | AI and Machine Learning ApplicationsResearch Track at Room 1 Chair(s): Stephan Krusche Technical University of Munich | ||
10:30 22mTalk | Leveraging Open Source LLMs for Software Engineering Education and Training Research Track Juanan Pereira , Juan Miguel Lopez , Xabier Garmendia , Maider Azanza University of the Basque Country (UPV/EHU) | ||
10:52 22mTalk | Navigating the AI Frontier: A Critical Literature Review on Integrating Artificial Intelligence into Software Engineering Education Research Track Chandan Kumar Sah Beihang University | ||
11:15 22mTalk | Adapting Computational Skills for AI Integration Research Track | ||
11:37 22mTalk | Towards Integrating Emerging AI Applications in SE Education Research Track Michael Vierhauser University of Innsbruck, Clemens Sauerwein University of Innsbruck, Tobias Antensteiner , Iris Groher Johannes Kepler University, Linz |
Enter the building and take the main stairs or elevator to the top floor.