A Personalised Learning Tool for Physics Undergraduate Students Built On a Large Language Model for Symbolic Regression

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhu, Yufan, Khoo, Zi-Yu, Low, Jonathan Sze Choong, Bressan, Stephane
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911937775796224
author Zhu, Yufan
Khoo, Zi-Yu
Low, Jonathan Sze Choong
Bressan, Stephane
author_facet Zhu, Yufan
Khoo, Zi-Yu
Low, Jonathan Sze Choong
Bressan, Stephane
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2407_00065
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Personalised Learning Tool for Physics Undergraduate Students Built On a Large Language Model for Symbolic Regression
Zhu, Yufan
Khoo, Zi-Yu
Low, Jonathan Sze Choong
Bressan, Stephane
Physics Education
Artificial Intelligence
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.
title A Personalised Learning Tool for Physics Undergraduate Students Built On a Large Language Model for Symbolic Regression
topic Physics Education
Artificial Intelligence
url https://arxiv.org/abs/2407.00065