On-Device Language Models for Privacy-Preserving Stress Prediction: A Multimodal Evaluation on Mobile Health
This work evaluates ODLMs for multi-modal stress prediction using zero-shot prompting, measuring predictive accuracy alongside latency and throughput, and shows that objective sensor features marginally outperform subjective self-reports on average and that lightweight sub-2B models achieve low latency with predictable...
Ibukunoluwa Soyebo, Alyssa Donawa, Rodrigo Aguilar Barrios et al.
· IEEE/ACM International Confe... · 0 citations