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

arXiv:2608.25771v1 Announce Type: cross Abstract: 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 with 12 patient-surrogate dyads, P4-DT predicted patient treatment choices with 81.7% accuracy, significantly exceeding chance (OR = 5.61 [2.03, 15.51], p < .001) and outperforming both unassisted surrogates (55.0%; OR = 3.67 [1.59, 8.47], p = .002) and surrogates assisted by P4-DT (61.7%). Comparative prompt analyses showed that incorporating contextual scenario decisions and open-ended text improved accuracy by 15.0 percentage points over initial values ratings alone. We discuss implications for further testing and designing of context-aware AI agents that embody richer human experience to partner in complex decision-making.

Related

• Who Gets the Kidney? Human-AI Alignment, Indecision, and Moral Values
• Response Time Enhances Alignment with Heterogeneous Preferences
• Behavioral and Representational Evidence of Binomial Ordering Preferences in Large Language Models

Source: arXiv cs.LG | 2026-08-27