设计中的共情：为医疗对话对齐大语言模型
Empathy by Design: Aligning Large Language Models for Healthcare Dialogue
AI总结：
本文提出基于DPO的对齐框架，通过优化医疗对话中事实准确性、语义连贯性和共情能力，提升AI助手在医疗场景中的可信度和人文关怀。
摘要：
通用的大语言模型（LLMs）在生成和推理能力方面表现出色，但在医疗和护理应用中仍受限于两个关键缺陷：事实不可靠性和缺乏共情沟通能力。这些不足在敏感情境中尤其危险，特别是在非专业人士和护理人员寻求医学相关指导或情感安慰时。为了解决这些挑战，我们引入了一个基于直接偏好优化（DPO）的对齐框架，旨在提高事实准确性、语义连贯性以及以人为中心的品质，如共情、礼貌和简洁性。我们的方法通过成对偏好数据微调领域适应的LLMs，其中优选响应反映支持性和易懂的沟通风格，而被拒绝的响应则代表指令性或过于技术性的语气。这种直接优化方法比传统的强化学习对齐方法更有效地将模型输出与人类偏好对齐。在多个开源和专有LLMs上的实证评估表明，我们的DPO微调模型在语义对齐、事实准确性以及人本评估得分方面优于基线和商业替代品，如谷歌医疗对话系统。这些改进表明，基于偏好的对齐方法为开发可信、富有同理心且临床信息丰富的AI助手提供了可扩展且透明的路径。我们的开源代码可在：https://github.com/LeonG19/Empathy-by-Design 上获得。
英文摘要：
General-purpose large language models (LLMs) have demonstrated remarkable generative and reasoning capabilities but remain limited in healthcare and caregiving applications due to two key deficiencies: factual unreliability and a lack of empathetic communication. These shortcomings pose significant risks in sensitive contexts where users, particularly non-professionals and caregivers, seek medically relevant guidance or emotional reassurance. To address these challenges, we introduce a Direct Preference Optimization (DPO)-based alignment framework designed to improve factual correctness, semantic coherence, and human-centric qualities such as empathy, politeness, and simplicity in caregiver-patient dialogues. Our approach fine-tunes domain-adapted LLMs using pairwise preference data, where preferred responses reflect supportive and accessible communication styles while rejected ones represent prescriptive or overly technical tones. This direct optimization method aligns model outputs with human preferences more efficiently than traditional reinforcement-learning-based alignment. Empirical evaluations across multiple open and proprietary LLMs show that our DPO-tuned models achieve higher semantic alignment, improved factual accuracy, and stronger human-centric evaluation scores compared to baseline and commercial alternatives such as Google medical dialogue systems. These improvements demonstrate that preference-based alignment offers a scalable and transparent pathway toward developing trustworthy, empathetic, and clinically informed AI assistants for caregiver and healthcare communication. Our open-source code is available at: https://github.com/LeonG19/Empathy-by-Design
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。
