What Does the AI Doctor Value? Auditing Pluralism in the Clinical Ethics of Language Models

TL;DR

This paper introduces a framework for auditing the value pluralism of medical language models, revealing their systematic biases and potential to undermine clinical diversity in ethical decision-making.

Contribution

It presents a novel benchmark and attribution method to analyze and compare the ethical value priorities of large language models in medicine.

Findings

Models exhibit physician-level heterogeneity in value priorities.

Models discuss competing values before making decisions.

Some models significantly underweight patient autonomy.

Abstract

Medicine is inherently pluralistic. Principles such as autonomy, beneficence, nonmaleficence, and justice routinely conflict, and such ethical dilemmas often sharply divide reasonable physicians. Good clinical practice navigates these tensions in concert with each patient's values rather than imposing a single ethical stance. The ethical values that large language models bring to medical advice, however, have not been systematically examined. We present a framework for auditing value pluralism in medical AI, comprising a benchmark of clinician-verified dilemmas and an attribution method that recovers value priorities directly from decisions. The ecosystem of frontier models spans physician-level value heterogeneity, and models discuss competing values in their reasoning (Overton pluralism) before committing to a decision. However, individual model decisions are near-deterministic across repeated sampling and semantic variations, failing to reproduce the distributional pluralism of the physician panel. Across benchmark cases, these consistent decisions reflect committed, systematic value preferences. While most model priorities fall within the natural range of inter-physician variation, some significantly underweight patient autonomy. A single LLM deployed without regard for its value priorities could amplify those priorities at scale to every patient it serves. Without explicit efforts to balance ethical perspectives with one or multiple models, these tools risk replacing clinical pluralism with a deployment monoculture.