RECAP: Transparent Inference-Time Emotion Alignment for Medical Dialogue Systems
This addresses the need for empathic communication in clinical contexts to support patient safety, adherence, and trust, representing a domain-specific incremental improvement.
The paper tackled the problem of large language models in healthcare delivering emotionally flat advice by introducing RECAP, an inference-time framework that improves emotional reasoning by 22-28% on 8B models and 10-13% on larger models over zero-shot baselines, as validated across benchmarks and clinician evaluations.
Large language models in healthcare often miss critical emotional cues, delivering medically sound but emotionally flat advice. This is especially problematic in clinical contexts where patients are distressed and vulnerable, and require empathic communication to support safety, adherence, and trust. We present RECAP (Reflect-Extract-Calibrate-Align-Produce), an inference-time framework that adds structured emotional reasoning without retraining. By decomposing empathy into transparent appraisal-theoretic stages and exposing per-dimension Likert signals, RECAP produces nuanced, auditable responses. Across EmoBench, SECEU, and EQ-Bench, RECAP improves emotional reasoning by 22-28% on 8B models and 10-13% on larger models over zero-shot baselines. Clinician evaluations further confirm superior empathetic communication. RECAP shows that modular, theory-grounded prompting can systematically enhance emotional intelligence in medical AI while preserving the accountability required for deployment.