From Generation to Collaboration: Using LLMs to Edit for Empathy in Healthcare
This work addresses the need for empathetic and trustworthy AI-assisted communication in healthcare, offering a safer pathway by shifting from autonomous generation to collaborative editing.
The study tackled the challenge of enhancing clinical empathy in written physician responses by using large language models as empathy editors, resulting in significantly increased perceived empathy while preserving factual accuracy compared to fully generated outputs.
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.