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

• URL: http://arxiv.org/abs/2604.12210v2
• Date: Thu, 16 Apr 2026 10:44:59 GMT
• Title: Beyond Prompt: Fine-grained Simulation of Cognitively Impaired Standardized Patients via Stochastic Steering
• Abstract summary: We propose StsPatient for the fine-grained simulation of cognitively impaired patients.<n>We capture domain-specific features by extracting steering vectors from contrastive pairs of instructions and responses.<n>StsPatient significantly outperforms baselines in both clinical authenticity and severity controllability.
• Score: 58.85421622061983
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Uncertainty-Aware Exploratory Direct Preference Optimization for Multimodal Large Language Models [53.15468578562038]
  We propose an Uncertainty-aware Exploratory Direct Preference Optimization (UE-DPO) method for Multimodal Large Language Models (MLLMs)<n>We first quantify the uncertainty from the model's failure to ground token predictions in the given image.<n>We then encourage more learning pressure on visually deficient tokens in preferred samples, and alleviate the over-penalization of beneficial knowledge in dispreferred samples.
  arXiv  Detail & Related papers  (2026-05-06T13:08:12Z)
• Towards Trustworthy Depression Estimation via Disentangled Evidential Learning [50.22167852149165]
  We propose EviDep, an evidential learning framework that jointly quantifies depression severity.<n>EviDep enforces strict information integrity to guarantee robust evidence synthesis.<n>It achieves state-of-the-art predictive accuracy and superior uncertainty calibration, delivering a robust fail-safe mechanism for trustworthy clinical screening.
  arXiv  Detail & Related papers  (2026-04-17T13:27:11Z)
• Information-Theoretic Optimization for Task-Adapted Compressed Sensing Magnetic Resonance Imaging [92.90858286761515]
  Task-adapted compressed sensing magnetic resonance imaging (CS-MRI) is emerging to address the specific demands of downstream clinical tasks.<n>We propose the first task-adapted CS-MRI from the information-theoretic perspective to simultaneously achieve probabilistic inference for uncertainty prediction.<n>We leverage amortized optimization and construct tractable variational bounds for mutual information to jointly optimize sampling, reconstruction, and task-inference models.
  arXiv  Detail & Related papers  (2026-04-14T13:23:19Z)
• Maximin Learning of Individualized Treatment Effect on Multi-Domain Outcomes [3.6198659497898937]
  We propose DRIFT, a new framework for estimating robust treatment effects from high-dimensional item-level data.<n> DRIFT learns latent constructs via generalized factor analysis, then constructs an anchored on-target uncertainty set.<n>By optimizing worst-case performance over this uncertainty set, DRIFT yields ITEs that are robust to underrepresented or unmeasured domains.
  arXiv  Detail & Related papers  (2026-03-28T03:50:22Z)
• Suppressing Prior-Comparison Hallucinations in Radiology Report Generation via Semantically Decoupled Latent Steering [94.37535002230504]
  We develop a training-free, inference-time control framework termed Semantically Decoupled Latent Steering.<n>Our approach constructs a semantic-free intervention vector via large language model (LLM)-driven semantic decomposition.<n>We show that our approach significantly reduces the probability of historical hallucinations.
  arXiv  Detail & Related papers  (2026-02-27T04:49:01Z)
• Dimension-reduced outcome-weighted learning for estimating individualized treatment regimes in observational studies [1.338174941551702]
  Individualized treatment regimes (ITRs) aim to improve clinical outcomes by assigning treatment based on patient-specific characteristics.<n>We propose a novel sufficient dimension reduction approach that targets the contrast between potential outcomes and identifies a low-dimensional subspace.<n>We show that the proposed method achieves universal consistency, i.e., its risk converges to the Bayes risk, under mild regularity conditions.
  arXiv  Detail & Related papers  (2026-01-11T05:38:08Z)
• A systematic evaluation of uncertainty quantification techniques in deep learning: a case study in photoplethysmography signal analysis [1.6690512882610855]
  Deep learning models can be used to continuously monitor physiological parameters outside of clinical settings.<n>There is risk of poor performance when deployed in practical measurement scenarios leading to negative patient outcomes.<n>Here we implement eight uncertainty (UQ) techniques to models trained on two clinically relevant prediction tasks.
  arXiv  Detail & Related papers  (2025-10-31T22:54:13Z)
• Distribution-Free Uncertainty Quantification in Mechanical Ventilation Treatment: A Conformal Deep Q-Learning Framework [2.5070297884580874]
  This study introduces ConformalDQN, a distribution-free conformal deep Q-learning approach for optimizing mechanical ventilation in intensive care units.<n>We trained and evaluated our model using ICU patient records from the MIMIC-IV database.
  arXiv  Detail & Related papers  (2024-12-17T06:55:20Z)
• Towards Reliable Medical Image Segmentation by Modeling Evidential Calibrated Uncertainty [57.023423137202485]
  Concerns regarding the reliability of medical image segmentation persist among clinicians.<n>We introduce DEviS, an easily implementable foundational model that seamlessly integrates into various medical image segmentation networks.<n>By leveraging subjective logic theory, we explicitly model probability and uncertainty for medical image segmentation.
  arXiv  Detail & Related papers  (2023-01-01T05:02:46Z)
• Probabilities Are Not Enough: Formal Controller Synthesis for Stochastic Dynamical Models with Epistemic Uncertainty [68.00748155945047]
  Capturing uncertainty in models of complex dynamical systems is crucial to designing safe controllers. Several approaches use formal abstractions to synthesize policies that satisfy temporal specifications related to safety and reachability. Our contribution is a novel abstraction-based controller method for continuous-state models with noise, uncertain parameters, and external disturbances.
  arXiv  Detail & Related papers  (2022-10-12T07:57:03Z)
• Can uncertainty boost the reliability of AI-based diagnostic methods in digital pathology? [3.8424737607413157]
  We evaluate if adding uncertainty estimates for DL predictions in digital pathology could result in increased value for the clinical applications. We compare the effectiveness of model-integrated methods (MC dropout and Deep ensembles) with a model-agnostic approach. Our results show that uncertainty estimates can add some reliability and reduce sensitivity to classification threshold selection.
  arXiv  Detail & Related papers  (2021-12-17T10:10:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.