At this year’s ED-Media conference, we also did a workshop on „Understanding the Core of LLMs as genAI -CollectiveGPT and Human Intelligence„. Find a short published summary about it.
Abstract:
This workshop provides an engaging and interactive exploration of Large Language Models (LLMs), with a focus on how they operate at a foundational level. Using CollectiveGPT, an educational chatbot developed by the Ed-Tech Research Community Graz, participants gained firsthand experience understanding the principles behind generative AI (genAI) systems such as ChatGPT. Designed for educators of all disciplines, the workshop demystifies key LLM concepts such as probability-based word prediction, contextual understanding, and the role of training data. Attendees generated texts and compare their results with real-time outputs from ChatGPT, highlighting the differences between human reasoning and AI prediction. Key topics include prompting techniques, context framing, training bias, misinformation, and ethical considerations in AI use. Participants explored system prompt injection techniques and developed advanced prompting skills to optimize responses from AI systems. This workshop empowered educators with the knowledge to critically evaluate and responsibly use AI tools in their teaching. By fostering AI literacy, attendees got clear understanding of how LLMs work and how they can be leveraged to enhance learning experiences across diverse educational settings.
[publication @ conference website]
[draft @ ResearchGate]
Reference: Brünner, B. & Ebner, M. (2025). Understanding the Core of LLMs as genAI – CollectiveGPT and Human Intelligence. In T. Bastiaens (Ed.), Proceedings of EdMedia + Innovate Learning (pp. 153-154). Barcelona, Spain: Association for the Advancement of Computing in Education (AACE). Retrieved June 14, 2025 from https://www.learntechlib.org/primary/p/226329/.