{"title":"Large-scale AI language systems display an emergent ability to reason by analogy","authors":"","doi":"10.1038/s41562-023-01671-0","DOIUrl":null,"url":null,"abstract":"Analogical reasoning is a hallmark of human intelligence, as it enables us to flexibly solve new problems without extensive practice. By using a wide range of tests, we demonstrate that GPT-3, a large-scale artificial intelligence language model, is capable of solving difficult analogy problems at a level comparable to human performance.","PeriodicalId":19074,"journal":{"name":"Nature Human Behaviour","volume":"7 9","pages":"1426-1427"},"PeriodicalIF":21.4000,"publicationDate":"2023-08-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Nature Human Behaviour","FirstCategoryId":"102","ListUrlMain":"https://www.nature.com/articles/s41562-023-01671-0","RegionNum":1,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"MULTIDISCIPLINARY SCIENCES","Score":null,"Total":0}
引用次数: 0
Abstract
Analogical reasoning is a hallmark of human intelligence, as it enables us to flexibly solve new problems without extensive practice. By using a wide range of tests, we demonstrate that GPT-3, a large-scale artificial intelligence language model, is capable of solving difficult analogy problems at a level comparable to human performance.
期刊介绍：
Nature Human Behaviour is a journal that focuses on publishing research of outstanding significance into any aspect of human behavior.The research can cover various areas such as psychological, biological, and social bases of human behavior.It also includes the study of origins, development, and disorders related to human behavior.The primary aim of the journal is to increase the visibility of research in the field and enhance its societal reach and impact.
京公网安备 11010802042870号
京ICP备2023020795号-1
分享
求助内容：
应助结果提醒方式：
扫码关注我们
