Beyond Prompt: Fine-grained Simulation of Cognitively Impaired Standardized Patients via Stochastic Steering

TL;DR

This paper introduces StsPatient, a novel method for fine-grained, controllable simulation of cognitively impaired standardized patients, improving realism and severity regulation in clinical training scenarios.

Contribution

It presents a new approach using contrastive instruction-response pairs and stochastic token modulation to better simulate and control cognitive impairments.

Findings

StsPatient outperforms baseline methods in clinical authenticity.

The method achieves precise control over impairment severity.

Experiments demonstrate improved heterogeneity capture of cognitive deficits.

Abstract

Simulating Standardized Patients with cognitive impairment offers a scalable and ethical solution for clinical training. However, existing methods rely on discrete prompt engineering and fail to capture the heterogeneity of deficits across varying domains and severity levels. To address this limitation, we propose StsPatient for the fine-grained simulation of cognitively impaired patients. We innovatively capture domain-specific features by extracting steering vectors from contrastive pairs of instructions and responses. Furthermore, we introduce a Stochastic Token Modulation (STM) mechanism to regulate the intervention probability. STM enables precise control over impairment severity while mitigating the instability of conventional vector methods. Comprehensive experiments demonstrate that StsPatient significantly outperforms baselines in both clinical authenticity and severity controllability.