AI Needs a Therapist: Columbia U & IBM’s SafeguardGPT Leverages Psychotherapy & RL to Build Healthy AI Systems

In the new paper Towards Healthy AI: Large Language Models Need Therapists Too, a team from Columbia University and IBM Research proposes SafeguardGPT, a framework that incorporates psychotherapy and reinforcement learning to correct the potentially harmful behaviours of AI chatbots.

ai ai chatbots ai systems artificial intelligence chatbot chatbots columbia university deep-neural-networks framework gpt ibm ibm research language language models large language models machine learning machine learning & data science ml paper reinforcement reinforcement learning research systems team technology therapists university