@inproceedings{kermani-etal-2025-systematic,
    title = "A Systematic Evaluation of {LLM} Strategies for Mental Health Text Analysis: Fine-tuning vs. Prompt Engineering vs. {RAG}",
    author = "Kermani, Arshia  and
      Perez-Rosas, Veronica  and
      Metsis, Vangelis",
    editor = "Zirikly, Ayah  and
      Yates, Andrew  and
      Desmet, Bart  and
      Ireland, Molly  and
      Bedrick, Steven  and
      MacAvaney, Sean  and
      Bar, Kfir  and
      Ophir, Yaakov",
    booktitle = "Proceedings of the 10th Workshop on Computational Linguistics and Clinical Psychology (CLPsych 2025)",
    month = may,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.clpsych-1.14/",
    doi = "10.18653/v1/2025.clpsych-1.14",
    pages = "172--180",
    ISBN = "979-8-89176-226-8",
    abstract = "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."
}