PatientsWithPersonality（PWP）：基于 HEXACO 人格参数化的真实患者模拟框架

Authors:Moritz Schlager, Friederike Jungmann, Samuel Schmidgall, Philipp Raffler, Franziska Hartl, Eva Wende, Paula Roßm"uller, Conrad Ketzer, Matthew Thompson, Justin Anthony Chen, Christina Chen, Avinatan Hassidim, Dale R. Webster, Yossi Matias, Yun Liu, Daniel Rueckert, Mike Schaekermann, Paul Hager

View PDF HTML (experimental)

Abstract:Realistic patient simulation is a key requirement for developing and testing clinical LLMs at scale without costly user studies. Existing simulators lack realism and controllability: they overshare information and miss the variability of real patient behavior. Here, we introduce PatientsWithPersonality (PWP), a patient simulation framework that generates realistic yet diverse patient responses through explicit personality parametrization over a latent patient state. Grounded in the six-dimensional HEXACO personality model, it gives fine-grained control over conversational style, cooperativeness, and information disclosure. We evaluate PWP in the first direct comparison of different patient simulators under a shared protocol, anchored in transcripts of real physician-patient encounters. Clinicians judge PWP conversations as realistic at least as often as the recorded encounters themselves and far more often than prior simulators, and almost never flag them as "too informative". Our simulator also reproduces the disclosure pacing of real patients, and its HEXACO-conditioned personality traits can be recovered by clinicians and an autorater. PWP further shows a substantially wider behavioral range than the closest baseline. In a downstream benchmark, LLMs interviewing patients simulated by PWP perform closest to how they perform on the real encounters, whereas prior simulators make the task easier. PWP thus provides a realistic, steerable, and diverse patient population for improving and benchmarking clinical LLMs.

Submission history

From: Moritz Schlager [view email]
[v1] Wed, 13 May 2026 15:26:15 UTC (684 KB)
[v2] Tue, 11 Aug 2026 12:48:31 UTC (690 KB)
[v3] Wed, 4 Nov 2026 10:40:52 UTC (876 KB)