SOURCE-LINKED INTELLIGENCE

Large Language Model Few-Shot Prompting with Dilemma Training Outperforms Human Surrogates in Predicting Patient Preferences

arXiv · AI, language, vision and robotics · article · Aug 26, 2026 · UTC

In serious illness, human surrogates often struggle to accurately predict patient preferences (68% accuracy), causing decision conflict. Personalized Patient Preference Predictor (P4) agents offer a potential solution, but prior prototypes treat values as static ratings, ignoring the contextual, situation-dependent nature of medical choices. Grounded in the 'logic of care', we present P4-DT (Dilemma Training), a P4 agent that constructs a patient decision policy by engaging users with varied medical dilemmas, eliciting individual preference reasoning through bi-directional training. In a study

Read original source ↗ Open in workspace

recordType

paper

region

Global