Ursula Holzmann, Sulekha Anand, Alexander Y Payumo
{"title":"The ChatGPT Fact-Check: Exploiting the Limitations of Generative AI to Develop Evidenced-Based Reasoning Skills in College Science Courses.","authors":"Ursula Holzmann, Sulekha Anand, Alexander Y Payumo","doi":"10.1152/advan.00142.2024","DOIUrl":null,"url":null,"abstract":"<p><p>Generative large language models (LLMs) like ChatGPT can quickly produce informative essays on various topics. However, the information generated cannot be fully trusted as artificial intelligence (AI) can make factual mistakes. This poses challenges for using such tools in college classrooms. To address this, an adaptable assignment called the ChatGPT Fact-Check was developed to teach students in college science courses the benefits of using LLMs for topic exploration while emphasizing the importance of validating its claims based on evidence. The assignment requires students to use ChatGPT to generate essays, evaluate AI-generated sources, and assess the validity of AI-generated scientific claims (based on experimental evidence in primary sources). The assignment reinforces student learning around responsible AI use for exploration while maintaining evidence-based skepticism. The assignment meets objectives around efficiently leveraging beneficial features of AI, distinguishing evidence types, and evidence-based claim evaluation. Its adaptable nature allows integration across diverse courses to teach students to responsibly use AI for learning while maintaining a critical stance.</p>","PeriodicalId":50852,"journal":{"name":"Advances in Physiology Education","volume":" ","pages":""},"PeriodicalIF":1.7000,"publicationDate":"2025-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Advances in Physiology Education","FirstCategoryId":"95","ListUrlMain":"https://doi.org/10.1152/advan.00142.2024","RegionNum":4,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"EDUCATION, SCIENTIFIC DISCIPLINES","Score":null,"Total":0}
引用次数: 0
Abstract
Generative large language models (LLMs) like ChatGPT can quickly produce informative essays on various topics. However, the information generated cannot be fully trusted as artificial intelligence (AI) can make factual mistakes. This poses challenges for using such tools in college classrooms. To address this, an adaptable assignment called the ChatGPT Fact-Check was developed to teach students in college science courses the benefits of using LLMs for topic exploration while emphasizing the importance of validating its claims based on evidence. The assignment requires students to use ChatGPT to generate essays, evaluate AI-generated sources, and assess the validity of AI-generated scientific claims (based on experimental evidence in primary sources). The assignment reinforces student learning around responsible AI use for exploration while maintaining evidence-based skepticism. The assignment meets objectives around efficiently leveraging beneficial features of AI, distinguishing evidence types, and evidence-based claim evaluation. Its adaptable nature allows integration across diverse courses to teach students to responsibly use AI for learning while maintaining a critical stance.
期刊介绍:
Advances in Physiology Education promotes and disseminates educational scholarship in order to enhance teaching and learning of physiology, neuroscience and pathophysiology. The journal publishes peer-reviewed descriptions of innovations that improve teaching in the classroom and laboratory, essays on education, and review articles based on our current understanding of physiological mechanisms. Submissions that evaluate new technologies for teaching and research, and educational pedagogy, are especially welcome. The audience for the journal includes educators at all levels: K–12, undergraduate, graduate, and professional programs.