The Biased Oracle: Assessing LLMs' Understandability and Empathy in Medical Diagnoses

TL;DR

This paper evaluates large language models' ability to generate understandable and empathetic medical explanations, revealing biases and complexity issues that impact equitable patient communication.

Contribution

It introduces a systematic assessment of LLMs' understandability and empathy in medical contexts, highlighting biases and the need for calibration.

Findings

LLMs adapt explanations based on socio-demographic variables

Generated content can be overly complex

Biases in affective empathy affect accessibility

Abstract

Large language models (LLMs) show promise for supporting clinicians in diagnostic communication by generating explanations and guidance for patients. Yet their ability to produce outputs that are both understandable and empathetic remains uncertain. We evaluate two leading LLMs on medical diagnostic scenarios, assessing understandability using readability metrics as a proxy and empathy through LLM-as-a-Judge ratings compared to human evaluations. The results indicate that LLMs adapt explanations to socio-demographic variables and patient conditions. However, they also generate overly complex content and display biased affective empathy, leading to uneven accessibility and support. These patterns underscore the need for systematic calibration to ensure equitable patient communication. The code and data are released: https://github.com/Jeffateth/Biased_Oracle