PanicToCalm: A Proactive Counseling Agent for Panic Attacks
This addresses the need for effective AI-driven counseling tools for individuals experiencing panic attacks, though it is incremental as it builds on existing methods with a new dataset and evaluation framework.
The paper tackles the problem of providing timely counseling for panic attacks by introducing PACER, a model trained on a new dataset (PACE) and evaluated with PanicEval, which outperforms baselines in counselor metrics and client affect improvement, with human evaluations showing it is preferred over general, CBT-based, and GPT-4 models in panic scenarios.
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 (Code is available at https://github.com/JihyunLee1/PanicToCalm ).