Exploring the Applications of Generative AI in High School STEM Education
Ishaan Masilamony
TL;DR
This study investigates the effects of generative AI on learning outcomes and engagement in high school STEM, focusing on AP and on-level physics. Using a quasi-experimental design, it compares four treatments—control, search engines (SE), generative AI (GAI), and a generative AI literacy program (GAI-LP)—across two physics curricula with pre/post assessments and student surveys. Results show that GAI alone can harm performance relative to control, while the AI literacy program mitigates negative effects and improves outcomes; SE often outperforms untrained GAI, and GAI-LP enhances understanding and engagement to some extent, though survey measures of impact are mixed. The findings underscore the importance of AI literacy in classrooms and suggest longer-term, cross-disciplinary studies to determine sustained benefits and equity implications, as well as the potential value of education-focused GAI tools in practice.
Abstract
In recent years, ChatGPT \cite{openai_2023_gpt4} along with Microsoft Copilot have become subjects of great discourse, particularly in the field of education. Prior research has hypothesized on potential impacts these tools could have on student learning and performance. These have primarily relied on trends from prior applications of technology in education and an understanding of the limitations and strengths of Generative AI in other applications. This study utilizes an experimental approach to analyze the impacts of Generative AI on high school STEM education (physics in particular). In accordance with most findings, generative AI does have some positive impact on student performance. However, our findings have shown that the most significant impact is an increase in student engagement with the subject.