PrinciplismQA: A Philosophy-Grounded Approach to Assessing LLM-Human Clinical Medical Ethics Alignment

TL;DR

PrinciplismQA is a systematic, philosophy-grounded assessment tool for evaluating ethical reasoning in clinical medical LLMs, revealing gaps in ethical alignment despite high knowledge accuracy.

Contribution

It introduces a validated, expert-validated question set based on Principlism to evaluate LLMs' clinical medical ethics reasoning systematically.

Findings

Recent models show significant ethical reasoning gaps.

High knowledge accuracy does not imply ethical alignment.

PrinciplismQA enables reproducible ethical evaluation.

Abstract

As medical LLMs transition to clinical deployment, assessing their ethical reasoning capability becomes critical. While achieving high accuracy on knowledge benchmarks, LLMs lack validated assessment for navigating ethical trade-offs in clinical decision-making where multiple valid solutions exist. Existing benchmarks lack systematic approaches to incorporate recognized philosophical frameworks and expert validation for ethical reasoning assessment. We introduce PrinciplismQA, a philosophy-grounded approach to assessing LLM clinical medical ethics alignment. Grounded in Principlism, our approach provides a systematic methodology for incorporating clinical ethics philosophy into LLM assessment design. PrinciplismQA comprises 3,648 expert-validated questions spanning knowledge assessment and clinical reasoning. Our expert-calibrated pipeline enables reproducible evaluation and models ethical biases. Evaluating recent models reveals significant ethical reasoning gaps despite high knowledge accuracy, demonstrating that knowledge-oriented training does not ensure clinical ethical alignment. PrinciplismQA provides a validated tool for assessing clinical AI deployment readiness.