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

A research study evaluated how four major large language models (GPT-5.2, Claude 4.5 Sonnet, Gemini 3 Pro, and DeepSeek-R1) respond to patient preferences in clinical decision-making scenarios. While all models acknowledged patient values, they showed modest actual recommendation shifting with value sensitivity indices ranging from 0.13 to 0.27, revealing gaps in how AI systems incorporate patient preferences into medical recommendations.

• →Four major LLM families showed significant variation in default clinical aggressiveness levels, ranging from 2.0 to 3.5 on a 5-point scale.
• →All models acknowledged patient values in 100% of non-control trials, but actual recommendation changes remained limited.
• →Value sensitivity indices were relatively low across all models, ranging from 0.13 to 0.27.
• →Decision-matrix and VIM self-report mitigations each improved directional concordance by 0.125 in testing.
• →The study provides empirical data for value disclosure labels proposed by clinical AI governance frameworks.