Problem
Research questions and friction points this paper is trying to address.
personalized sleep guidance
wearable data
large language model (LLM)
privacy and accessibility
lightweight local deployment
Toward Personalized Sleep Guidance from Wearable Data Using Language Models
🤖 AI Summary
本文针对个性化睡眠指导问题，提出一种两阶段框架，利用多代理大语言模型从可穿戴设备数据生成结构化建议，并通过小语言模型增强推理。
📝 Abstract
Sleep monitoring using wearable data has shown promise for personal health, yet large language model (LLM)-based summarization and question answering remain insufficient for personalized sleep guidance. Training specialized models, however, often requires costly expert annotation. Moreover, privacy and accessibility concerns motivate lightweight, local deployment for end users. We present a two-stage framework to address these challenges. Specifically, in Stage~1, a multi-agent LLM pipeline reasons structured sleep guidance from unannotated wearable records, enabling scalable dataset construction. Stage~2 distills guidance reasoning trajectories into small language models (SLMs) through supervised fine-tuning and integrates a training-free Best-of-$N$ selection strategy to enhance inference. Experimental results demonstrate our method outperforms commercial general and medical LLMs and open-source models. Human evaluation further supports the quality of the generated guidance and the feasibility of personalized sleep guidance with SLMs.
Innovation
Methods, ideas, or system contributions that make the work stand out.
multi-agent LLM pipeline
structured sleep guidance
small language models (SLMs)
supervised fine-tuning
Best-of-N selection strategy
🔎 Similar Papers
No similar papers found.
💼 Related Jobs
No related jobs found.
