Speaker
Description
Artificial intelligence is transforming the landscape of education, offering new ways to enhance learning experiences and personalize feedback. This interactive workshop explores how AI can support multimedia-based assessment and feedback in physics education, focusing on its application in laboratory settings. Specifically, we will demonstrate how Large Language Models (LLMs), such as OpenAI’s GPT-4, can function as AI lab assistants to support student learning and engagement.
Participants will engage in a hands-on session where they will conduct a short physics lab experiment and interact with an AI-based assistant designed for physics laboratories. The AI assistant, developed at Portland State University, provides real-time support by verifying answers, guiding students toward correct solutions, and offering theoretical explanations. The workshop will offer insights into both the front end and back end of the AI assistant, illustrating how interactions are recorded, analyzed, and used for improving AI-driven feedback.
We will discuss findings from recent research on the integration of LLMs in physics education, focusing on students’ perspectives and expert assessments of AI-generated responses. Our study revealed that while LLMs can be beneficial for answer verification and conceptual guidance, they also pose challenges, such as the potential for incorrect or misleading feedback. Participants will explore these benefits and challenges firsthand, gaining practical experience in working with AI-assisted physics labs.
Through interactive demonstrations and discussions, attendees will develop an understanding of how AI can enhance multimedia-based assessment and feedback in physics education. By the end of the session, participants will be equipped with the knowledge and experience necessary to evaluate and potentially implement AI-based assistants in their own educational settings. This workshop is ideal for educators and researchers interested in leveraging AI to improve student engagement and learning outcomes in physics laboratories.
| Contribution categories - primary focus | University |
|---|---|
| Contribution categories - type | Application (shared experience, activity suggestions) |
