Jiatong Ma

LLMs excel in binary classifications but struggle dramatically with complex psychiatric diagnoses, revealing critical gaps in AI-assisted mental health tools.

Today's best multimodal LLMs still struggle to grasp fine-grained details and reason across multiple entities in images, even with access to external knowledge.

Achieve more accurate psychiatric diagnoses and empathetic interactions by grounding LLM agents in a clinical reasoning bank and explicitly rewarding rubric-based reasoning steps.