SleepCoT: A Lightweight Personalized Sleep Health Model via Chain-of-Thought Distillation

TL;DR

SleepCoT introduces a lightweight, personalized sleep health model that distills complex reasoning and expert knowledge from large language models into smaller, efficient models for practical health management.

Contribution

The paper presents a novel few-shot Chain-of-Thought distillation method enabling small models to perform comparably to large models in personalized sleep health recommendations.

Findings

Model achieves performance close to large LLMs in sleep health tasks

Significant improvements over baseline small models in reasoning and knowledge application

Efficient deployment suitable for real-world personalized healthcare

Abstract

We present a novel approach to personalized sleep health management using few-shot Chain-of-Thought (CoT) distillation, enabling small-scale language models (> 2B parameters) to rival the performance of large language models (LLMs) in specialized health domains. Our method simultaneously distills problem-solving strategies, long-tail expert knowledge, and personalized recommendation capabilities from larger models into more efficient, compact models. Unlike existing systems, our approach offers three key functionalities: generating personalized sleep health recommendations, supporting user-specific follow-up inquiries, and providing responses to domain-specific knowledge questions. We focus on sleep health due to its measurability via wearable devices and its impact on overall well-being. Our experimental setup, involving GPT-4o for data synthesis, Qwen-max for instruction set creation, and Qwen2.5 1.5B for model distillation, demonstrates significant improvements over baseline small-scale models in penalization, reasoning, and knowledge application. Experiments using 100 simulated sleep reports and 1,000 domain-specific questions shows our model achieves comparable performance to larger models while maintaining efficiency for real-world deployment. This research not only advances AI-driven health management but also provides a novel approach to leveraging LLM capabilities in resource-constrained environments, potentially enhancing the accessibility of personalized healthcare solutions.