The Value Sensitivity Gap: How Clinical Large Language Models Respond to Patient Preference Statements in Shared Decision-Making

TL;DR

This study evaluates how different clinical large language models respond to patient preference statements in shared decision-making, revealing their value sensitivity, response consistency, and potential for improved alignment with patient values.

Contribution

It provides empirical data on LLMs' responses to patient preferences, highlighting their value sensitivity and informing clinical AI governance frameworks.

Findings

Models acknowledged patient values in all non-control trials.

Directional concordance with patient preferences ranged from 0.625 to 1.0.

Decision-matrix and VIM mitigations improved concordance by 0.125.

Abstract

Large language models (LLMs) are entering clinical workflows as decision support tools, yet how they respond to explicit patient value statements -- the core content of shared decision-making -- remains unmeasured. We conducted a factorial experiment using clinical vignettes derived from 98,759 de-identified Medicaid encounter notes. We tested four LLM families (GPT-5.2, Claude 4.5 Sonnet, Gemini 3 Pro, and DeepSeek-R1) across 13 value conditions in two clinical domains, yielding 104 trials. Default value orientations differed across model families (aggressiveness range 2.0 to 3.5 on a 1-to-5 scale). Value sensitivity indices ranged from 0.13 to 0.27, and directional concordance with patient-stated preferences ranged from 0.625 to 1.0. All models acknowledged patient values in 100% of non-control trials, yet actual recommendation shifting remained modest. Decision-matrix and VIM self-report mitigations each improved directional concordance by 0.125 in a 78-trial Phase 2 evaluation. These findings provide empirical data for populating value disclosure labels proposed by clinical AI governance frameworks.