Exploring the potential of using ChatGPT in physics education

Yicong LIANG; Di ZOU; Haoran XIE; Fu Lee WANG

doi:10.1186/s40561-023-00273-7

Exploring the potential of using ChatGPT in physics education

Yicong LIANG, Di ZOU, Haoran XIE, Fu Lee WANG

Research output: Journal Publications › Journal Article (refereed) › peer-review

14 Citations (Scopus)

Abstract

The pretrained large language models have been widely tested for their performance on some challenging tasks including arithmetic, commonsense, and symbolic reasoning. Recently how to combine LLMs with prompting techniques has attracted lots of researchers to propose their models to automatically solve math word problems. However, most research works focus on solving math problems at the elementary school level and few works aim to solve problems in science disciplines, e.g., Physics. In this exploratory study, we discussed the potential pedagogical benefits of using ChatGPT in physics and demonstrated how to prompt ChatGPT in solving physics problems. The results suggest that ChatGPT is able to solve some physics calculation problems, explain solutions, and generate new exercises at a human level.

Original language	English
Article number	52
Journal	Smart Learning Environments
Volume	10
Issue number	1
DOIs	https://doi.org/10.1186/s40561-023-00273-7
Publication status	Published - 20 Oct 2023

Bibliographical note

The research has been supported by the Direct Grant (DR23B2) and the Faculty Research Grants (DB23A3 and DB23B2) of Lingnan University, Hong Kong.

Publisher Copyright:
© 2023, Springer Nature Singapore Pte Ltd., part of Springer Nature.

Keywords

AI in education
ChatGPT
Physics calculation problem
Physics learning

Access to Document

10.1186/s40561-023-00273-7Licence: CC BY

Cite this

@article{a72d2b4c73a342e1ae1bf25a63255088,

title = "Exploring the potential of using ChatGPT in physics education",

abstract = "The pretrained large language models have been widely tested for their performance on some challenging tasks including arithmetic, commonsense, and symbolic reasoning. Recently how to combine LLMs with prompting techniques has attracted lots of researchers to propose their models to automatically solve math word problems. However, most research works focus on solving math problems at the elementary school level and few works aim to solve problems in science disciplines, e.g., Physics. In this exploratory study, we discussed the potential pedagogical benefits of using ChatGPT in physics and demonstrated how to prompt ChatGPT in solving physics problems. The results suggest that ChatGPT is able to solve some physics calculation problems, explain solutions, and generate new exercises at a human level.",

keywords = "AI in education, ChatGPT, Physics calculation problem, Physics learning",

author = "Yicong LIANG and Di ZOU and Haoran XIE and WANG, {Fu Lee}",

note = "The research has been supported by the Direct Grant (DR23B2) and the Faculty Research Grants (DB23A3 and DB23B2) of Lingnan University, Hong Kong. Publisher Copyright: {\textcopyright} 2023, Springer Nature Singapore Pte Ltd., part of Springer Nature.",

year = "2023",

month = oct,

day = "20",

doi = "10.1186/s40561-023-00273-7",

language = "English",

volume = "10",

journal = "Smart Learning Environments",

issn = "2196-7091",

publisher = "Springer Open",

number = "1",

}

TY - JOUR

T1 - Exploring the potential of using ChatGPT in physics education

AU - LIANG, Yicong

AU - ZOU, Di

AU - XIE, Haoran

AU - WANG, Fu Lee

N1 - The research has been supported by the Direct Grant (DR23B2) and the Faculty Research Grants (DB23A3 and DB23B2) of Lingnan University, Hong Kong. Publisher Copyright: © 2023, Springer Nature Singapore Pte Ltd., part of Springer Nature.

PY - 2023/10/20

Y1 - 2023/10/20

N2 - The pretrained large language models have been widely tested for their performance on some challenging tasks including arithmetic, commonsense, and symbolic reasoning. Recently how to combine LLMs with prompting techniques has attracted lots of researchers to propose their models to automatically solve math word problems. However, most research works focus on solving math problems at the elementary school level and few works aim to solve problems in science disciplines, e.g., Physics. In this exploratory study, we discussed the potential pedagogical benefits of using ChatGPT in physics and demonstrated how to prompt ChatGPT in solving physics problems. The results suggest that ChatGPT is able to solve some physics calculation problems, explain solutions, and generate new exercises at a human level.

AB - The pretrained large language models have been widely tested for their performance on some challenging tasks including arithmetic, commonsense, and symbolic reasoning. Recently how to combine LLMs with prompting techniques has attracted lots of researchers to propose their models to automatically solve math word problems. However, most research works focus on solving math problems at the elementary school level and few works aim to solve problems in science disciplines, e.g., Physics. In this exploratory study, we discussed the potential pedagogical benefits of using ChatGPT in physics and demonstrated how to prompt ChatGPT in solving physics problems. The results suggest that ChatGPT is able to solve some physics calculation problems, explain solutions, and generate new exercises at a human level.

KW - AI in education

KW - ChatGPT

KW - Physics calculation problem

KW - Physics learning

UR - http://www.scopus.com/inward/record.url?scp=85174594438&partnerID=8YFLogxK

U2 - 10.1186/s40561-023-00273-7

DO - 10.1186/s40561-023-00273-7

M3 - Journal Article (refereed)

SN - 2196-7091

VL - 10

JO - Smart Learning Environments

JF - Smart Learning Environments

IS - 1

M1 - 52

ER -

Exploring the potential of using ChatGPT in physics education

Abstract

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Contrastive Sentence Representation Learning with Adaptive False Negative Cancellation

Integrating Novel Dropout Mechanism into Label Extension for Emotion Classification

Cite this

Exploring the potential of using ChatGPT in physics education

Abstract

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Projects

Contrastive Sentence Representation Learning with Adaptive False Negative Cancellation

Integrating Novel Dropout Mechanism into Label Extension for Emotion Classification

Cite this