Investigating ChatGPT-4’s performance in solving physics problems and its potential implications for education

IF 2.3 3区教育学 Q1 EDUCATION & EDUCATIONAL RESEARCH

Asia Pacific Education Review Pub Date : 2023-11-29 DOI:10.1007/s12564-023-09913-6

Dazhen Tong, Yang Tao, Kangkang Zhang, Xinxin Dong, Yangyang Hu, Sudong Pan, Qiaoyi Liu

{"title":"Investigating ChatGPT-4’s performance in solving physics problems and its potential implications for education","authors":"Dazhen Tong, Yang Tao, Kangkang Zhang, Xinxin Dong, Yangyang Hu, Sudong Pan, Qiaoyi Liu","doi":"10.1007/s12564-023-09913-6","DOIUrl":null,"url":null,"abstract":"<div><p>Artificial intelligence (AI) technologies have been consistently influencing the progress of education for an extended period, with its impact becoming more significant especially after the launch of ChatGPT-3.5 at the end of November 2022. In the field of physics education, recent research regarding the performance of ChatGPT-3.5 in solving physics problems discovered that its problem-solving abilities were only at the level of novice students, insufficient to cause outstanding alarm in the field of physics education. However, the release of ChatGPT-4 presented substantial improvements in reasoning and conciseness. How does this translate to performance in solving physics problems, and what kind of impact might it have on education? This study undertakes a comprehensive assessment of ChatGPT-4’s performance in solving physics problems from the perspective of physics conceptual understanding and reasoning, and compares its performance with that of students. It is concluded that ChatGPT-4’s performance in solving physics problems has significantly improved compared to ChatGPT-3.5, and was notably superior to the majority of middle school and high school students. This finding presents both a challenge and an opportunity for physics education and the broader educational field, and triggers immediate considerations for coping with this challenge in future teaching and assessment environments.</p></div>","PeriodicalId":47344,"journal":{"name":"Asia Pacific Education Review","volume":null,"pages":null},"PeriodicalIF":2.3000,"publicationDate":"2023-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Asia Pacific Education Review","FirstCategoryId":"95","ListUrlMain":"https://link.springer.com/article/10.1007/s12564-023-09913-6","RegionNum":3,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"EDUCATION & EDUCATIONAL RESEARCH","Score":null,"Total":0}

引用次数: 0

Abstract

Artificial intelligence (AI) technologies have been consistently influencing the progress of education for an extended period, with its impact becoming more significant especially after the launch of ChatGPT-3.5 at the end of November 2022. In the field of physics education, recent research regarding the performance of ChatGPT-3.5 in solving physics problems discovered that its problem-solving abilities were only at the level of novice students, insufficient to cause outstanding alarm in the field of physics education. However, the release of ChatGPT-4 presented substantial improvements in reasoning and conciseness. How does this translate to performance in solving physics problems, and what kind of impact might it have on education? This study undertakes a comprehensive assessment of ChatGPT-4’s performance in solving physics problems from the perspective of physics conceptual understanding and reasoning, and compares its performance with that of students. It is concluded that ChatGPT-4’s performance in solving physics problems has significantly improved compared to ChatGPT-3.5, and was notably superior to the majority of middle school and high school students. This finding presents both a challenge and an opportunity for physics education and the broader educational field, and triggers immediate considerations for coping with this challenge in future teaching and assessment environments.

Abstract Image

查看原文本刊更多论文

研究ChatGPT-4在解决物理问题方面的表现及其对教育的潜在影响

人工智能(AI)技术长期以来一直影响着教育的进步，尤其是在2022年11月底推出ChatGPT-3.5之后，其影响变得更加显著。在物理教育领域，最近对ChatGPT-3.5在解决物理问题方面的研究发现，其解决问题的能力仅处于初学者的水平，不足以在物理教育领域引起突出的警示。然而，ChatGPT-4的发布在推理和简洁性方面有了实质性的改进。这如何转化为解决物理问题的表现，它对教育可能产生什么样的影响?本研究从物理概念理解和推理的角度对ChatGPT-4在解决物理问题方面的表现进行了综合评估，并与学生的表现进行了比较。结果表明，ChatGPT-4在解决物理问题方面的能力较ChatGPT-3.5有了显著提高，明显优于大多数初高中学生。这一发现为物理教育和更广泛的教育领域提出了挑战和机遇，并引发了在未来的教学和评估环境中应对这一挑战的直接考虑。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Asia Pacific Education Review EDUCATION & EDUCATIONAL RESEARCH-

CiteScore

5.20

自引率

4.30%

发文量

期刊介绍： The Asia Pacific Education Review (APER) aims to stimulate research, encourage academic exchange, and enhance the professional development of scholars and other researchers who are interested in educational and cultural issues in the Asia Pacific region. APER covers all areas of educational research, with a focus on cross-cultural, comparative and other studies with a broad Asia-Pacific context. APER is a peer reviewed journal produced by the Education Research Institute at Seoul National University. It was founded by the Institute of Asia Pacific Education Development, Seoul National University in 2000, which is owned and operated by Education Research Institute at Seoul National University since 2003. APER requires all submitted manuscripts to follow the seventh edition of the Publication Manual of the American Psychological Association (APA; http://www.apastyle.org/index.aspx).