用大模型当编辑，让医患沟通更温暖又准确。
From Generation to Collaboration: Using LLMs to Edit for Empathy in Healthcare
- 让大模型充当编辑，优化医生文书的共情语气。
- 编辑后文本感知共情度提升，事实准确性不变。
- 适合想提升医疗沟通质量的AI辅助系统开发者。
临床共情对患者照护至关重要，但医生在临床实践中需在情感温度与事实精确性之间持续权衡，受认知和情绪限制。本研究探讨大语言模型（LLMs）作为共情编辑器的潜力，通过润色医生书面回应来增强共情表达，同时保留原有医学信息。我们引入两项新量化指标：共情评分（Empathy Ranking Score）和医学事实核查得分（MedFactChecking Score），系统评估回应的情感与事实质量。实验表明，经LLM编辑后的文本显著提升共情感知度，同时保持事实准确性，优于完全由大模型生成的内容。结果表明，将大模型作为编辑助手而非自主生成者，是实现可信且富有同理心的AI医疗沟通更安全、有效的路径。
原文摘要 · Abstract (English)
Clinical empathy is essential for patient care, but physicians need continually balance emotional warmth with factual precision under the cognitive and emotional constraints of clinical practice. This study investigates how large language models (LLMs) can function as empathy editors, refining physicians' written responses to enhance empathetic tone while preserving underlying medical information. More importantly, we introduce novel quantitative metrics, an Empathy Ranking Score and a MedFactChecking Score to systematically assess both emotional and factual quality of the responses. Experimental results show that LLM edited responses significantly increase perceived empathy while preserving factual accuracy compared with fully LLM generated outputs. These findings suggest that using LLMs as editorial assistants, rather than autonomous generators, offers a safer, more effective pathway to empathetic and trustworthy AI-assisted healthcare communication.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。