Using Prompt Engineering to Enhance STEM Education
A prototype tool with prompt engineering to fully utilize the educational potential of LLMs and reduce usage for academic dishonesty is developed and will enhance the STEP education by AI.
Abstract
With the advent of large language models (LLMs), such as ChatGPT, Gemini and LLaMA, there is no doubt that AI will forever change how education works. However, there is a gap between K-12 students and the LLM. The prompts given to LLM need to be well designed to be effectively utilized for K-12 education. To use LLMs more appropriately for K-12 STEM educational purposes, the author developed a prototype tool with prompt engineering to fully utilize the educational potential of LLMs and reduce usage for academic dishonesty. The tool would have a student register by giving the grade that they're in, and then ask as the topic the student would like to learn more about. Using prompt engineering techniques, the tool can prompt LLMs to produce educational content such as a descriptions, question and answer, AI-generated quizzes, and reviews, as well as asking the LLM to simplifying complex topics further to aid in understanding. The AI-enabled tool, effectively a virtual and personal mentor, could help propel STEM education further and make STEM more interesting to students as it could help explain complex topics in a way that students can understand easily. The tool and AI can help students understand a topic through interactive practice instead of just memorizing facts and putting them on a sheet of paper. The tool present in this paper will enhance the STEP education by AI.