Teymoor Khosravi, Zainab M. Al Sudani, Morteza Oladnabi
{"title":"ChatGPT在多大程度上了解遗传学?","authors":"Teymoor Khosravi, Zainab M. Al Sudani, Morteza Oladnabi","doi":"10.1080/14703297.2023.2258842","DOIUrl":null,"url":null,"abstract":"ABSTRACTOpenAI’s ChatGPT, is a conversational chatbot that uses Generative Pre-trained Transformer or GPT language model to mimic human-like responses. Here we evaluated its performance in providing responses to genetics questions across five different tasks including solid genetic basics, identifying inheritance pattern based on described pedigrees, interpreting genetic mutation notations, solving genetic population problems, and taking a medical genetics Ph.D. entrance exam. Our results showed that ChatGPT was able to generate correct answers to approximately 70% of questions (n = 145). Its performance on descriptive and memorisation tasks showed more accuracy compared to analytical and critical thinking ones. Failure to capture human writing nuances in questions, and applying genetic basics to solve problems, alongside providing false information were the most notable drawbacks. However, overall results were promising suggesting that ChatGPT could be a well-prepared assistant for genetic educators and healthcare providers.KEYWORDS: ChatGPTgenerative pre-trained transformergeneticsartificial intelligencelarge language model AcknowledgmentsThis study was supported by the Golestan University of Medical Sciences (Grant Number: 13350).Disclosure statementNo potential conflict of interest was reported by the author(s).Data availability statementNo additional data were created or used in this study beyond what is presented in the manuscript.EthicsThis study was ethically approved by Ethics Committee of Golestan University of Medical Sciences (Ethics Code: IR.GOUMS.REC.1401.522)Supplementary materialSupplemental data for this article can be accessed online at https://doi.org/10.1080/14703297.2023.2258842Additional informationFundingThis work was supported by the Golestan University of Medical Sciences and Health Services [113350].Notes on contributorsTeymoor KhosraviTeymoor Khosravi is a postgraduate student at Golestan university of medical sciences studying human genetics.Zainab M. Al SudaniZainab M. Al Sudani is a medical student at Golestan university of medical sciences.Morteza OladnabiMorteza Oladnabi is an associate professor of medical genetics working at Gorgan congenital malformations research center.","PeriodicalId":47628,"journal":{"name":"Innovations in Education and Teaching International","volume":"41 1","pages":"0"},"PeriodicalIF":1.9000,"publicationDate":"2023-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"To what extent does ChatGPT understand genetics?\",\"authors\":\"Teymoor Khosravi, Zainab M. Al Sudani, Morteza Oladnabi\",\"doi\":\"10.1080/14703297.2023.2258842\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"ABSTRACTOpenAI’s ChatGPT, is a conversational chatbot that uses Generative Pre-trained Transformer or GPT language model to mimic human-like responses. Here we evaluated its performance in providing responses to genetics questions across five different tasks including solid genetic basics, identifying inheritance pattern based on described pedigrees, interpreting genetic mutation notations, solving genetic population problems, and taking a medical genetics Ph.D. entrance exam. Our results showed that ChatGPT was able to generate correct answers to approximately 70% of questions (n = 145). Its performance on descriptive and memorisation tasks showed more accuracy compared to analytical and critical thinking ones. Failure to capture human writing nuances in questions, and applying genetic basics to solve problems, alongside providing false information were the most notable drawbacks. However, overall results were promising suggesting that ChatGPT could be a well-prepared assistant for genetic educators and healthcare providers.KEYWORDS: ChatGPTgenerative pre-trained transformergeneticsartificial intelligencelarge language model AcknowledgmentsThis study was supported by the Golestan University of Medical Sciences (Grant Number: 13350).Disclosure statementNo potential conflict of interest was reported by the author(s).Data availability statementNo additional data were created or used in this study beyond what is presented in the manuscript.EthicsThis study was ethically approved by Ethics Committee of Golestan University of Medical Sciences (Ethics Code: IR.GOUMS.REC.1401.522)Supplementary materialSupplemental data for this article can be accessed online at https://doi.org/10.1080/14703297.2023.2258842Additional informationFundingThis work was supported by the Golestan University of Medical Sciences and Health Services [113350].Notes on contributorsTeymoor KhosraviTeymoor Khosravi is a postgraduate student at Golestan university of medical sciences studying human genetics.Zainab M. Al SudaniZainab M. Al Sudani is a medical student at Golestan university of medical sciences.Morteza OladnabiMorteza Oladnabi is an associate professor of medical genetics working at Gorgan congenital malformations research center.\",\"PeriodicalId\":47628,\"journal\":{\"name\":\"Innovations in Education and Teaching International\",\"volume\":\"41 1\",\"pages\":\"0\"},\"PeriodicalIF\":1.9000,\"publicationDate\":\"2023-09-14\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Innovations in Education and Teaching International\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1080/14703297.2023.2258842\",\"RegionNum\":4,\"RegionCategory\":\"教育学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"EDUCATION & EDUCATIONAL RESEARCH\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Innovations in Education and Teaching International","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1080/14703297.2023.2258842","RegionNum":4,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"EDUCATION & EDUCATIONAL RESEARCH","Score":null,"Total":0}
引用次数: 0
摘要
topenai的ChatGPT是一个会话聊天机器人,它使用生成式预训练转换器或GPT语言模型来模仿人类的反应。在这里,我们评估了它在五个不同任务中的表现,包括扎实的遗传基础,根据描述的谱系识别遗传模式,解释基因突变符号,解决遗传群体问题,以及参加医学遗传学博士入学考试。我们的结果表明,ChatGPT能够为大约70%的问题生成正确答案(n = 145)。它在描述性和记忆任务上的表现比分析性和批判性思维任务更准确。最明显的缺点是未能捕捉到问题中人类文字的细微差别,并应用遗传基础来解决问题,同时提供错误的信息。然而,总体结果是有希望的,这表明ChatGPT可以成为遗传教育者和医疗保健提供者的一个准备充分的助手。关键词:chatgpt生成预训练转化遗传人工智能大型语言模型致谢本研究得到了Golestan医学科学大学(资助号:13350)的支持。披露声明作者未报告潜在的利益冲突。数据可用性声明本研究未创建或使用除手稿中提供的数据外的其他数据。本研究经戈列斯坦医科大学伦理委员会伦理批准(伦理代码:IR.GOUMS.REC.1401.522)。补充材料。本文补充资料可在https://doi.org/10.1080/14703297.2023.2258842Additional information网站上获取。作者简介:steymoor Khosravi是Golestan医学科学大学研究人类遗传学的研究生。Zainab M. Al Sudani是Golestan医科大学的一名医科学生。Morteza Oladnabi是戈尔根先天性畸形研究中心的医学遗传学副教授。
ABSTRACTOpenAI’s ChatGPT, is a conversational chatbot that uses Generative Pre-trained Transformer or GPT language model to mimic human-like responses. Here we evaluated its performance in providing responses to genetics questions across five different tasks including solid genetic basics, identifying inheritance pattern based on described pedigrees, interpreting genetic mutation notations, solving genetic population problems, and taking a medical genetics Ph.D. entrance exam. Our results showed that ChatGPT was able to generate correct answers to approximately 70% of questions (n = 145). Its performance on descriptive and memorisation tasks showed more accuracy compared to analytical and critical thinking ones. Failure to capture human writing nuances in questions, and applying genetic basics to solve problems, alongside providing false information were the most notable drawbacks. However, overall results were promising suggesting that ChatGPT could be a well-prepared assistant for genetic educators and healthcare providers.KEYWORDS: ChatGPTgenerative pre-trained transformergeneticsartificial intelligencelarge language model AcknowledgmentsThis study was supported by the Golestan University of Medical Sciences (Grant Number: 13350).Disclosure statementNo potential conflict of interest was reported by the author(s).Data availability statementNo additional data were created or used in this study beyond what is presented in the manuscript.EthicsThis study was ethically approved by Ethics Committee of Golestan University of Medical Sciences (Ethics Code: IR.GOUMS.REC.1401.522)Supplementary materialSupplemental data for this article can be accessed online at https://doi.org/10.1080/14703297.2023.2258842Additional informationFundingThis work was supported by the Golestan University of Medical Sciences and Health Services [113350].Notes on contributorsTeymoor KhosraviTeymoor Khosravi is a postgraduate student at Golestan university of medical sciences studying human genetics.Zainab M. Al SudaniZainab M. Al Sudani is a medical student at Golestan university of medical sciences.Morteza OladnabiMorteza Oladnabi is an associate professor of medical genetics working at Gorgan congenital malformations research center.
期刊介绍:
Innovations in Education and Teaching International (IETI), is the journal of the Staff and Educational Development Association (SEDA) www.seda.ac.uk. As such, contributions to the Journal should reflect SEDA"s aim to promote innovation and good practice in higher education through staff and educational development and subject-related practices. Contributions are welcomed on any aspect of promoting and supporting educational change in higher and other post-school education, with an emphasis on research, experience, scholarship and evaluation, rather than mere description of practice.