Exploring the potential of using ChatGPT in physics education

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 so...

Full description

Saved in:
Bibliographic Details
Published inSmart Learning Environments Vol. 10; no. 1; pp. 52 - 19
Main Authors Liang, Yicong, Zou, Di, Xie, Haoran, Wang, Fu Lee
Format Journal Article
LanguageEnglish
Published Singapore Springer Nature Singapore 01.12.2023
Springer
Springer Nature B.V
SpringerOpen
Subjects
Online AccessGet full text

Cover

Loading…
More Information
Summary: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.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2196-7091
2196-7091
DOI:10.1186/s40561-023-00273-7