{"title":"Fusing ChatGPT and Human Decisions in Unfamiliar Face Matching","authors":"Robin S. S. Kramer","doi":"10.1002/acp.70037","DOIUrl":null,"url":null,"abstract":"<p>Unfamiliar face matching involves deciding whether two face images depict the same person or two different people. Individual performance can be error-prone but is improved by aggregating (fusing) the responses of participant pairs. With advances in automated facial recognition systems (AFR), fusing human and algorithm responses also leads to performance improvements over individuals working alone. In the current work, I investigated whether ChatGPT could serve as the algorithm in this fusion. Using a common face matching test, I found that the fusion of individual responses with those provided by ChatGPT increased performance in comparison with both individuals working alone and simulated participant pairs. This pattern of results was evident when participants responded either using a rating scale (Experiment 1) or with a binary decision and associated confidence (Experiment 2). Taken together, these findings demonstrate the potential utility of ChatGPT in daily identification contexts where state-of-the-art AFR may not be available.</p>","PeriodicalId":48281,"journal":{"name":"Applied Cognitive Psychology","volume":"39 2","pages":""},"PeriodicalIF":2.1000,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/acp.70037","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Applied Cognitive Psychology","FirstCategoryId":"102","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1002/acp.70037","RegionNum":3,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"PSYCHOLOGY, EXPERIMENTAL","Score":null,"Total":0}
引用次数: 0
Abstract
Unfamiliar face matching involves deciding whether two face images depict the same person or two different people. Individual performance can be error-prone but is improved by aggregating (fusing) the responses of participant pairs. With advances in automated facial recognition systems (AFR), fusing human and algorithm responses also leads to performance improvements over individuals working alone. In the current work, I investigated whether ChatGPT could serve as the algorithm in this fusion. Using a common face matching test, I found that the fusion of individual responses with those provided by ChatGPT increased performance in comparison with both individuals working alone and simulated participant pairs. This pattern of results was evident when participants responded either using a rating scale (Experiment 1) or with a binary decision and associated confidence (Experiment 2). Taken together, these findings demonstrate the potential utility of ChatGPT in daily identification contexts where state-of-the-art AFR may not be available.
期刊介绍：
Applied Cognitive Psychology seeks to publish the best papers dealing with psychological analyses of memory, learning, thinking, problem solving, language, and consciousness as they occur in the real world. Applied Cognitive Psychology will publish papers on a wide variety of issues and from diverse theoretical perspectives. The journal focuses on studies of human performance and basic cognitive skills in everyday environments including, but not restricted to, studies of eyewitness memory, autobiographical memory, spatial cognition, skill training, expertise and skilled behaviour. Articles will normally combine realistic investigations of real world events with appropriate theoretical analyses and proper appraisal of practical implications.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
