Unsophisticated AI coaching does not improve performance on symptom and performance validity tests in a Romanian sample of experimental feigners.

IF 1.4 4区心理学 Q4 CLINICAL NEUROLOGY

Applied Neuropsychology-Adult Pub Date : 2025-05-31 DOI:10.1080/23279095.2025.2512786

Samira Voin, Iulia Crișan, Florin Alin Sava

{"title":"Unsophisticated AI coaching does not improve performance on symptom and performance validity tests in a Romanian sample of experimental feigners.","authors":"Samira Voin, Iulia Crișan, Florin Alin Sava","doi":"10.1080/23279095.2025.2512786","DOIUrl":null,"url":null,"abstract":"The present study aimed to investigate the ability of symptom and performance validity indicators to detect experimental feigning with symptom-coaching vs. AI assistance. Fifty-nine undergraduates and community members (45 females, MAge=22.6, SDAge=2.1; MEducation=14.5, SDEducation=1.4) were randomized into three experimental groups: controls (n = 20), symptom-coached feigners (n = 20), and AI-coached feigners (n = 19). The two feigning groups were instructed to feign a mild traumatic brain injury (TBI) for evading work responsibilities. All participants were assessed online with the Inventory of Problems-29 and its memory module (IOP-29-M) and the Memory of Objects and Digits and Examination of Memory Malingering Test (MODEMM). Results indicated that AI-coached participants exaggerated symptomatology and underperformed significantly more compared to the symptom-coached group. All validity indicators of the IOP-29-M and MODEMM discriminated between experimental feigners and control participants at previously reported cutoffs with high sensitivities (.69-1.00) and excellent specificities (.95-1.00). Our findings contribute to nascent research on feigning with AI assistance, also providing proof of concept for the accuracy of the IOP-29-M and MODEMM in detecting symptom-coached and AI-coached feigning.","PeriodicalId":51308,"journal":{"name":"Applied Neuropsychology-Adult","volume":" ","pages":"1-8"},"PeriodicalIF":1.4000,"publicationDate":"2025-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Applied Neuropsychology-Adult","FirstCategoryId":"102","ListUrlMain":"https://doi.org/10.1080/23279095.2025.2512786","RegionNum":4,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"CLINICAL NEUROLOGY","Score":null,"Total":0}

引用次数: 0

Abstract

The present study aimed to investigate the ability of symptom and performance validity indicators to detect experimental feigning with symptom-coaching vs. AI assistance. Fifty-nine undergraduates and community members (45 females, M_Age=22.6, SD_Age=2.1; M_Education=14.5, SD_Education=1.4) were randomized into three experimental groups: controls (n = 20), symptom-coached feigners (n = 20), and AI-coached feigners (n = 19). The two feigning groups were instructed to feign a mild traumatic brain injury (TBI) for evading work responsibilities. All participants were assessed online with the Inventory of Problems-29 and its memory module (IOP-29-M) and the Memory of Objects and Digits and Examination of Memory Malingering Test (MODEMM). Results indicated that AI-coached participants exaggerated symptomatology and underperformed significantly more compared to the symptom-coached group. All validity indicators of the IOP-29-M and MODEMM discriminated between experimental feigners and control participants at previously reported cutoffs with high sensitivities (.69-1.00) and excellent specificities (.95-1.00). Our findings contribute to nascent research on feigning with AI assistance, also providing proof of concept for the accuracy of the IOP-29-M and MODEMM in detecting symptom-coached and AI-coached feigning.

查看原文本刊更多论文

在罗马尼亚的实验假人样本中，简单的人工智能训练并不能提高症状和表现有效性测试的表现。

本研究旨在探讨症状和表现效度指标在症状指导和人工智能辅助下检测实验假装的能力。59名大学生及社区成员(女性45名，MAge=22.6, SDAge=2.1；meeducation =14.5, education =1.4)被随机分为3个实验组：对照组（n = 20）、症状指导假牙组（n = 20）和ai指导假牙组（n = 19）。两个假装组被要求假装轻度创伤性脑损伤（TBI）以逃避工作责任。所有参与者都通过问题清单-29及其记忆模块（io -29- m）和物体和数字的记忆和记忆伪造检查测试（MODEMM）进行在线评估。结果表明，与症状指导组相比，人工智能训练的参与者夸大了症状，表现不佳。iop29 - m和MODEMM的所有效度指标在先前报道的截止点上区分实验假名者和对照参与者，具有高灵敏度（0.69 -1.00）和极好的特异性（0.95 -1.00）。我们的研究结果有助于人工智能辅助下的伪造研究，也为io -29- m和MODEMM在检测症状指导和人工智能指导的伪造方面的准确性提供了概念证明。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Applied Neuropsychology-Adult CLINICAL NEUROLOGY-PSYCHOLOGY

CiteScore

4.50

自引率

11.80%

发文量

134

期刊介绍： pplied Neuropsychology-Adult publishes clinical neuropsychological articles concerning assessment, brain functioning and neuroimaging, neuropsychological treatment, and rehabilitation in adults. Full-length articles and brief communications are included. Case studies of adult patients carefully assessing the nature, course, or treatment of clinical neuropsychological dysfunctions in the context of scientific literature, are suitable. Review manuscripts addressing critical issues are encouraged. Preference is given to papers of clinical relevance to others in the field. All submitted manuscripts are subject to initial appraisal by the Editor-in-Chief, and, if found suitable for further considerations are peer reviewed by independent, anonymous expert referees. All peer review is single-blind and submission is online via ScholarOne Manuscripts.