{"title":"Multimodal Generative Artificial Intelligence Tackles Visual Problems in Chemistry","authors":"Eman A. Alasadi, and , Carlos R. Baiz*, ","doi":"10.1021/acs.jchemed.4c00138","DOIUrl":null,"url":null,"abstract":"<p >The introduction of multimodal capabilities in large language models (LLMs) marks a significant advancement in the field of artificial intelligence (AI). In particular, the ability to process and interpret visual data, including complex graphs and plots frequently encountered in chemistry, expands the potential of these models. This integration of text and image processing allows multimodal AI to tackle a broader range of problems, especially in areas where visual information is central to understanding and solving problems. This study provides an examination of GPT-4’s image input capabilities, specifically targeting its efficacy in interpreting and solving chemistry problems that require graphical information. This study evaluates GPT-4’s image input feature, focusing on its accuracy in interpreting chemical diagrams, structures, and tabular data, and its utility as an interactive, conversational tutor in chemistry education. The research assesses the consistency of the AI’s responses to visual data of varying quality and its ability to parse handwritten problems and answers. Further, the study examines GPT-4’s capacity for molecular structure analysis and spectral data interpretation, vital for advanced problem-solving in chemistry. Through analysis, we demonstrate how the image processing capabilities of GPT-4 could be leveraged for pedagogical purposes, particularly in undergraduate chemistry courses. In addition, we provide advice for prompt development to improve response quality.</p>","PeriodicalId":43,"journal":{"name":"Journal of Chemical Education","volume":null,"pages":null},"PeriodicalIF":2.5000,"publicationDate":"2024-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Chemical Education","FirstCategoryId":"92","ListUrlMain":"https://pubs.acs.org/doi/10.1021/acs.jchemed.4c00138","RegionNum":3,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"CHEMISTRY, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0
Abstract
The introduction of multimodal capabilities in large language models (LLMs) marks a significant advancement in the field of artificial intelligence (AI). In particular, the ability to process and interpret visual data, including complex graphs and plots frequently encountered in chemistry, expands the potential of these models. This integration of text and image processing allows multimodal AI to tackle a broader range of problems, especially in areas where visual information is central to understanding and solving problems. This study provides an examination of GPT-4’s image input capabilities, specifically targeting its efficacy in interpreting and solving chemistry problems that require graphical information. This study evaluates GPT-4’s image input feature, focusing on its accuracy in interpreting chemical diagrams, structures, and tabular data, and its utility as an interactive, conversational tutor in chemistry education. The research assesses the consistency of the AI’s responses to visual data of varying quality and its ability to parse handwritten problems and answers. Further, the study examines GPT-4’s capacity for molecular structure analysis and spectral data interpretation, vital for advanced problem-solving in chemistry. Through analysis, we demonstrate how the image processing capabilities of GPT-4 could be leveraged for pedagogical purposes, particularly in undergraduate chemistry courses. In addition, we provide advice for prompt development to improve response quality.
期刊介绍:
The Journal of Chemical Education is the official journal of the Division of Chemical Education of the American Chemical Society, co-published with the American Chemical Society Publications Division. Launched in 1924, the Journal of Chemical Education is the world’s premier chemical education journal. The Journal publishes peer-reviewed articles and related information as a resource to those in the field of chemical education and to those institutions that serve them. JCE typically addresses chemical content, activities, laboratory experiments, instructional methods, and pedagogies. The Journal serves as a means of communication among people across the world who are interested in the teaching and learning of chemistry. This includes instructors of chemistry from middle school through graduate school, professional staff who support these teaching activities, as well as some scientists in commerce, industry, and government.