@inproceedings{bn-etal-2025-pursuit,
    title = "The Pursuit of Empathy: Evaluating Small Language Models for {PTSD} Dialogue Support",
    author = "Bn, Suhas  and
      Mahajan, Yash  and
      Mattioli, Dominik O.  and
      Sherrill, Andrew M.  and
      Arriaga, Rosa I.  and
      Wiese, Christopher  and
      Abdullah, Saeed",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.1573/",
    pages = "30888--30910",
    ISBN = "979-8-89176-332-6",
    abstract = "This paper investigates the capacity of small language models (0.5B-5B parameters) to generate empathetic responses for individuals with PTSD. We introduce Trauma-Informed Dialogue for Empathy (TIDE), a novel dataset comprising 10,000 two-turn conversations across 500 diverse, clinically-grounded PTSD personas (https://huggingface.co/datasets/yenopoya/TIDE). Using frontier model outputs as ground truth, we evaluate eight small LLMs in zero-shot settings and after fine-tuning. Fine-tuning enhances empathetic capabilities, improving cosine similarity and perceived empathy, although gains vary across emotional scenarios and smaller models exhibit a ``knowledge transfer ceiling.'' As expected, Claude Sonnet 3.5 consistently outperforms all models, but surprisingly, the smaller models often approach human-rated empathy levels. Demographic analyses showed that older adults favored responses that validated distress before offering support (p = .004), while graduate-educated users preferred emotionally layered replies in specific scenarios. Gender-based differences were minimal (p {\ensuremath{>}} 0.15), suggesting the feasibility of broadly empathetic model designs. This work offers insights into building resource-efficient, emotionally intelligent systems for mental health support."
}