@inproceedings{lee-etal-2025-panictocalm,
    title = "{P}anic{T}o{C}alm: A Proactive Counseling Agent for Panic Attacks",
    author = "Lee, Jihyun  and
      Min, Yejin  and
      Kim, San  and
      Jeon, Yejin  and
      Yang, Sung Jun  and
      Kim, Hyounghun  and
      Lee, Gary",
    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.649/",
    pages = "12853--12885",
    ISBN = "979-8-89176-332-6",
    abstract = "Panic attacks are acute episodes of fear and distress, in which timely, appropriate intervention can significantly help individuals regain stability. However, suitable datasets for training such models remain scarce due to ethical and logistical issues. To address this, we introduce Pace, which is a dataset that includes high-distress episodes constructed from first-person narratives, and structured around the principles of Psychological First Aid (PFA). Using this data, we train Pacer, a counseling model designed to provide both empathetic and directive support, which is optimized through supervised learning and simulated preference alignment. To assess its effectiveness, we propose PanicEval, a multi-dimensional framework covering general counseling quality and crisis-specific strategies. Experimental results show that Pacer outperforms strong baselines in both counselor-side metrics and client affect improvement. Human evaluations further confirm its practical value, with Pacer consistently preferred over general, CBT-based, and GPT-4-powered models in panic scenarios."
}