When conviction outpaces evidence: diagnostic boundary failures of large language models in adult ADHD self-assessment
Large language models (LLMs) are increasingly used by people seeking information about possible mental-health conditions, including attention-deficit/hyperactivity disorder (ADHD). This raises an important safety question: can these systems distinguish between stronger clinical evidence and a user’s increasing confidence in a self-diagnosis? We evaluated ChatGPT, Gemini, and Doubao using 24…
Read original article on Frontiers in Psychiatry | New and Recent Articles →Related news
-
12 Mindful Quotes We Need to Read Every Morning for the Rest of the Year
United States
-
Experience-Sampling Method
United Kingdom
-
‘Ananta: Spirit of Coltrane’
United States
-
10 Life Choices You Will Absolutely Regret in 10 Years (and Maybe Even Sooner)
United States
-
A cross-sectional and longitudinal examination of adolescents’ emotion expression flexibility and their self-injurious thoughts and behaviors
Switzerland
-
Comparative efficacy of different digital technologies in adults with insomnia: a systematic review and network meta-analysis of randomized controlled trials
Switzerland
-
The role of overgeneralized autobiographical memories and inflammatory markers in stress symptoms associated with the COVID-19 pandemic
Switzerland
-
Family office psychiatry: a new concept for the mental health treatment of ultra-high net-worth individuals
Switzerland