AI 中文总结
本研究评估设备端语言模型在移动健康中利用零样本提示进行多模态压力预测的可行性，发现客观传感器特征略优且轻量级模型低延迟，凸显其潜力与约束。
AI 中文摘要
压力是心理健康的普遍决定因素，也是移动健康干预的关键目标。设备端语言模型（ODLMs）在不依赖云端的情况下提供隐私保护的推理，但其在移动资源约束下用于健康预测的可行性仍未得到充分探索。我们使用零样本提示评估ODLMs在多模态压力预测中的表现，同时测量预测准确性以及延迟和吞吐量。结果表明，客观传感器特征在平均性能上略优于主观自我报告，且轻量级子2B模型实现了低延迟和可预测的资源使用。我们的发现既凸显了ODLMs在移动心理健康领域的潜力，也揭示了其实际约束。
英文摘要
Stress is a pervasive determinant of mental health and a key target for mobile health interventions. On-device language models (ODLMs) offer privacy-preserving inference without cloud dependency, yet their feasibility for health prediction under mobile resource constraints remains underexplored. We evaluate ODLMs for multi-modal stress prediction using zero-shot prompting, measuring predictive accuracy alongside latency and throughput. Our results show that objective sensor features marginally outperform subjective self-reports on average, and that lightweight sub-2B models achieve low latency with predictable resource usage. Our findings highlight both the promise and the practical constraints of ODLMs for mobile mental health.
Comments6 pages, 2 figures. Received Honorable Mention at the 2026 Human-centered AI Research for Mental health, an Open Networking Symposium (HARMONY 2026) workshop, co-located with IEEE/ACM Conference on Connected Health: Applications, Systems, and Engineering Technologies (CHASE 2026)
