Geriatric Attitude of ChatGPT4.o and Its Evaluation by Social Workers
Huai Cheng, Jill Vinge

TL;DR
This study evaluates ChatGPT4.o's geriatric attitude using a validated instrument and compares it to human responses, finding that it shows less age bias than humans.
Contribution
The study is the first to assess ChatGPT4.o's geriatric attitudes using a validated instrument and compare them with social workers' evaluations.
Findings
ChatGPT4.o had a higher positive geriatric attitude score (4.2) than humans.
ChatGPT4.o had a lower negative geriatric attitude score (1.8) than humans.
Social workers modestly agreed with ChatGPT4.o's geriatric attitude responses.
Abstract
Ageism is global and prevalent in healthcare. Previous studies have shown that ChatGPT generated gender and racial biased outputs. This study aimed to explore ChatGPT4.o geriatric attitude using validated UCLA geriatric attitude instrument and to compare it with health trainees and providers and to examine whether hospital social workers agree or disagree with ChatGPT 4.o responses to geriatric attitude statements. Six of 16 statements reflected positive geriatric attitudes, such as “Most old people are pleasant to be with”. Ten statements reflected negative geriatric attitudes, such as “Treatment of chronically ill old patients is hopeless”. ChatGPT4.o responses and social workers’ evaluation of ChatGPT4.o responses were graded on a Likert scale of 1-5 (1=strongly disagree, 5 =strongly agree). Positive and negative geriatric attitudes scores were calculated to compare them to the…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsArtificial Intelligence in Healthcare and Education · Digital Mental Health Interventions · Aging and Gerontology Research
