This study presents a systematic comparison of three approaches for the analysis of mental health text using large language models (LLMs): prompt engineering, retrieval augmented generation (RAG), and fine-tuning. Using LLaMA 3, we evaluate these approaches on emotion classification and mental health condition detection tasks across two datasets. Fine-tuning achieves the highest accuracy (91% for emotion classification, 80% for mental health conditions) but requires substantial computational resources and large training sets, while prompt engineering and RAG offer more flexible deployment with moderate performance (40-68% accuracy). Our findings provide practical insights for implementing LLM-based solutions in mental health applications, highlighting the trade-offs between accuracy, computational requirements, and deployment flexibility.

本研究系统比较了三种使用大型语言模型（LLMs）进行心理健康文本分析的方法：提示工程、检索增强生成（RAG）和微调。研究发现微调方法在情感分类和心理健康状况检测任务中表现最佳，但需消耗大量计算资源和训练数据，而提示工程和RAG则提供了更灵活的部署选项，尽管性能适中。这一发现为心理健康应用中的LLM解决方案实施提供了实用见解，突出了准确性、计算需求和部署灵活性之间的权衡。

针对心理健康文本分析的大型语言模型策略的系统评估：微调、提示工程与检索增强生成