MentalAgora: A Gateway to Advanced Personalized Care in Mental Health through Multi-Agent Debating and Attribute Control
This addresses the need for advanced digital mental health interventions for individuals seeking tailored care, representing a domain-specific advancement.
The paper tackles the problem of providing personalized mental health support by introducing MentalAgora, a framework using multi-agent debating with large language models, which generates expert-aligned responses and meets user preferences, as validated through experiments and user studies on the TherapyTalk dataset.
As mental health issues globally escalate, there is a tremendous need for advanced digital support systems. We introduce MentalAgora, a novel framework employing large language models enhanced by interaction between multiple agents for tailored mental health support. This framework operates through three stages: strategic debating, tailored counselor creation, and response generation, enabling the dynamic customization of responses based on individual user preferences and therapeutic needs. We conduct experiments utilizing a high-quality evaluation dataset TherapyTalk crafted with mental health professionals, shwoing that MentalAgora generates expert-aligned and user preference-enhanced responses. Our evaluations, including experiments and user studies, demonstrate that MentalAgora aligns with professional standards and effectively meets user preferences, setting a new benchmark for digital mental health interventions.