VERA-MH: Validation of Ethical and Responsible AI in Mental Health

ArXi:2605.13318v1 Announce Type: new Chatbot usage has increased, including in fields for which they were never developed for--notably mental health. To that end, we VERA-MH is comprised of three steps: conversation simulation, conversation judging and model rating. First, to simulate conversations with the chatbot under evaluation, another chatbot is tasked with role-playing users based on specific personas. Such user personas have been developed under clinical guidance, to make sure that, among others, multiple risk factors, graphic characteristics and disclosure factors were represented.