PROJECTS
Safe and Responsible Mental Health AI
This project evaluates and strengthens the safety, quality, and reliability of AI-powered mental health chatbots. It combines domain-specific constitutional principles with systematic evaluation of harmful, inconsistent, or inappropriate responses to support more responsible conversational mental health technologies.
Ongoing research (publication forthcoming)
- Evaluating the Safety, Quality, and Reliability of Mental Health Chatbots
Project information
- Category: Large Language Models and Mental Health
- Contact Person: Amir M. Rahmani
