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

arXiv: https://arxiv.org/abs/2511.00924 · HTML: https://mlsanity.com/paper/2511.00924/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 45 references that are in the map.
- First posted on arXiv 2 Nov 2025.

## Builds on (most cited first, 7 of 7)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [A Survey on LLM-as-a-Judge](https://mlsanity.com/paper/2411.15594/) (2024)
- [Limitations of the LLM-as-a-Judge Approach for Evaluating LLM Outputs in Expert Knowledge Tasks](https://mlsanity.com/paper/2410.20266/) (2024)
- [Style Over Substance: Evaluation Biases for Large Language Models](https://mlsanity.com/paper/2307.03025/) (2023)
- [Comparing Two Model Designs for Clinical Note Generation; Is an LLM a Useful Evaluator of Consistency?](https://mlsanity.com/paper/2404.06503/) (2024)
- [Towards Leveraging Large Language Models for Automated Medical Q&A Evaluation](https://mlsanity.com/paper/2409.01941/) (2024)
- [DiversityMedQA: Assessing Demographic Biases in Medical Diagnosis using Large Language Models](https://mlsanity.com/paper/2409.01497/) (2024)

## Built on by (most cited first, 1 of 1)

- [QuarkMedBench: A Real-World Scenario Driven Benchmark for Evaluating Large Language Models](https://mlsanity.com/paper/2603.13691/) (2026)

## Abstract (arXiv)

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