A Personalised Learning Tool for Physics Undergraduate Students Built On a Large Language Model for Symbolic Regression
This work addresses the problem of providing immediate, personalized attention to undergraduate physics students to improve their problem-solving skills, though it is incremental as it builds on existing methods like LLMs and dimensional analysis.
The researchers tackled the challenge of enhancing undergraduate physics education by developing a personalized learning tool that uses a Large Language Model for symbolic regression and dimensional analysis to help students understand relationships between physics variables. The tool correctly identified variable relationships for most equations from Feynman's lectures, demonstrating its effectiveness as a complementary educational aid.
Interleaved practice enhances the memory and problem-solving ability of students in undergraduate courses. We introduce a personalized learning tool built on a Large Language Model (LLM) that can provide immediate and personalized attention to students as they complete homework containing problems interleaved from undergraduate physics courses. Our tool leverages the dimensional analysis method, enhancing students' qualitative thinking and problem-solving skills for complex phenomena. Our approach combines LLMs for symbolic regression with dimensional analysis via prompt engineering and offers students a unique perspective to comprehend relationships between physics variables. This fosters a broader and more versatile understanding of physics and mathematical principles and complements a conventional undergraduate physics education that relies on interpreting and applying established equations within specific contexts. We test our personalized learning tool on the equations from Feynman's lectures on physics. Our tool can correctly identify relationships between physics variables for most equations, underscoring its value as a complementary personalized learning tool for undergraduate physics students.