FedMentalCare: Towards Privacy-Preserving Fine-Tuned LLMs to Analyze Mental Health Status Using Federated Learning Framework
This work addresses privacy issues for mental healthcare applications, but it appears incremental as it applies existing techniques (FL and LoRA) to a specific domain.
The paper tackles the privacy concerns of using Large Language Models (LLMs) in mental healthcare by proposing FedMentalCare, a framework that combines Federated Learning with Low-Rank Adaptation to fine-tune LLMs, demonstrating a scalable and privacy-aware approach for real-world deployment.
With the increasing prevalence of mental health conditions worldwide, AI-powered chatbots and conversational agents have emerged as accessible tools to support mental health. However, deploying Large Language Models (LLMs) in mental healthcare applications raises significant privacy concerns, especially regarding regulations like HIPAA and GDPR. In this work, we propose FedMentalCare, a privacy-preserving framework that leverages Federated Learning (FL) combined with Low-Rank Adaptation (LoRA) to fine-tune LLMs for mental health analysis. We investigate the performance impact of varying client data volumes and model architectures (e.g., MobileBERT and MiniLM) in FL environments. Our framework demonstrates a scalable, privacy-aware approach for deploying LLMs in real-world mental healthcare scenarios, addressing data security and computational efficiency challenges.