From Generation to Collaboration: Using LLMs to Edit for Empathy in Healthcare

TL;DR

This paper explores how large language models can serve as empathy editors in healthcare communication, enhancing emotional warmth in physicians' responses while maintaining factual accuracy, and introduces new metrics for assessment.

Contribution

It introduces novel quantitative metrics for evaluating empathy and factual accuracy in LLM-edited healthcare responses and demonstrates the effectiveness of LLMs as editorial tools.

Findings

LLM-edited responses significantly increase perceived empathy.

LLM editing preserves factual accuracy better than fully generated responses.

Using LLMs as editors is safer and more effective than autonomous generation.

Abstract

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.