RECAP：医疗对话系统中透明的推理时间情感对齐
RECAP: Transparent Inference-Time Emotion Alignment for Medical Dialogue Systems
AI总结：
RECAP通过结构化情感推理提升医疗对话系统的情感响应质量，实现透明和可审计的同理心沟通。
摘要：
医疗领域的大型语言模型常常遗漏关键的情感线索，提供医学上正确但情感平淡的建议。这样的回应在临床接触中是不足的，因为在沮丧或脆弱的患者中，他们依赖富有同理心的沟通来支持安全、依从性和信任。我们提出了RECAP（反思-提取-校准-对齐-生成），一个在推理时间指导模型通过结构化情感推理而无需重新训练的框架。RECAP将患者输入分解为 appraisal-理论阶段，识别心理因素，并分配基于Likert的情感可能性，这些临床医生可以检查或覆盖，从而产生细腻且可审计的回应。在EmoBench、SECEU和EQ-Bench上，RECAP在8B模型上提高了22-28%的情感推理，在更大模型上提高了10-13%相对于零样本基线。在盲评中，肿瘤科医生认为RECAP的回应比提示基线更富有同理心、支持性和情境合适。这些发现表明，模块化、原则性的提示可以增强医疗AI的情感智能，同时在临床部署中保持透明和问责。
英文摘要：
Large language models in healthcare often miss critical emotional cues, delivering medically sound but emotionally flat advice. Such responses are insufficient in clinical encounters, where distressed or vulnerable patients rely on empathic communication to support safety, adherence, and trust. We present RECAP (Reflect-Extract-Calibrate-Align-Produce), an inference-time framework that guides models through structured emotional reasoning without retraining. RECAP decomposes patient input into appraisal-theoretic stages, identifies psychological factors, and assigns Likert-based emotion likelihoods that clinicians can inspect or override, producing nuanced and 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. In blinded evaluations, oncology clinicians rated RECAP's responses as more empathetic, supportive, and context-appropriate than prompting baselines. These findings demonstrate that modular, principled prompting can enhance emotional intelligence in medical AI while maintaining transparency and accountability for clinical deployment.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
