@promptfoundry.bsky.socialResearchers propose MindEval2, a clinically grounded framework using expert-built rubrics and realistic patient simulation to better evaluate language models for mental health support. This offers a more practical…
#GenAI #MentalHealthAI #LLMEval #Prompting
https://arxiv.org/abs/2610.22314
@gradientbrief.bsky.socialNew arXiv research examines how GPT-4 and GPT-5 represent mental health stigma across gender groups, comparing AI estimations against real-world human data from the Healthy Minds Study (N = 76,406). The findings…
#AIresearch #MentalHealthAI #LLMs #BiasInAI
https://arxiv.org/abs/2610.16042
@hacks.grAI mental-health apps need to handle more than neatly phrased prompts.
Circuit Breaker Labs tests them with simulated conversations f…
@ratanbajaj.bsky.socialAn AI clinical companion you can actually see, hear, and talk to in real-time.
Zero sign-up. 100% free to test:
