mlsanityData to 14 Oct 2026

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

arXiv 2604.12210 ↗First posted 14 Apr 2026cs.AI cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 23 of its 82 references that are in the map. First posted on arXiv 14 Apr 2026.

Builds on

23 of 82 references.

References · 23

  1. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  2. 2023Steering Llama 2 via Contrastive Activation Additioncited by 1,085
  3. 2025Persona Vectors: Monitoring and Controlling Character Traits in Language Modelscited by 345
  4. 2024Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Modelscited by 235
  5. 2024Large Language Models are Superpositions of All Characters: Attaining Arbitrary Role-play via Self-Alignmentcited by 104
  6. 2024Roleplay-doh: Enabling Domain-Experts to Create LLM-simulated Patients via Eliciting and Adhering to Principlescited by 73
  7. 2024Cactus: Towards Psychological Counseling Conversations using Cognitive Behavioral Theorycited by 60
  8. 2024The Oscars of AI Theater: A Survey on Role-Playing with Language Modelscited by 48
  9. 2024Interactive Agents: Simulating Counselor-Client Psychological Counseling via Role-Playing LLM-to-LLM Interactionscited by 43
  10. 2020Generate, Delete and Rewrite: A Three-Stage Framework for Improving Persona Consistency of Dialogue Generationcited by 41
  11. 2024Automatic Interactive Evaluation for Large Language Models with State Aware Patient Simulatorcited by 39
  12. 2024LLMs Can Simulate Standardized Patients via Agent Coevolutioncited by 22
11 more
  1. 2024Leveraging Large Language Model as Simulated Patients for Clinical Educationcited by 21
  2. 2025Cross-model Transferability among Large Language Models on the Platonic Representations of Conceptscited by 12
  3. 2025Improving LLM Reasoning through Interpretable Role-Playing Steeringcited by 12
  4. 2019A Review of Automated Speech and Language Features for Assessment of Cognitive and Thought Disorderscited by 11
  5. 2023A Cognitive Stimulation Dialogue System with Multi-source Knowledge Fusion for Elders with Cognitive Impairmentcited by 10
  6. 2024Concept -- An Evaluation Protocol on Conversational Recommender Systems with System-centric and User-centric Factorscited by 9
  7. 2025Adaptive-VP: A Framework for LLM-Based Virtual Patients that Adapts to Trainees' Dialogue to Facilitate Nurse Communication Trainingcited by 9
  8. 2025Modeling Challenging Patient Interactions: LLMs for Medical Communication Trainingcited by 7
  9. 2025Designing Role Vectors to Improve LLM Inference Behaviourcited by 6
  10. 2023A Digital Language Coherence Marker for Monitoring Dementiacited by 4
  11. 2024MedDiT: A Knowledge-Controlled Diffusion Transformer Framework for Dynamic Medical Image Generation in Virtual Simulated Patientcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025A Multi-faceted Analysis of Cognitive Abilities: Evaluating Prompt Methods with Large Language Models on the CONSORT Checklist
  2. 2025Diffusion with a Linguistic Compass: Steering the Generation of Clinically Plausible Future sMRI Representations for Early MCI Conversion Prediction
  3. 2026Cerebra: A Multidisciplinary AI Board for Multimodal Dementia Characterization and Risk Assessment
  4. 2026Toward Personalized Digital Twins for Cognitive Decline Assessment: A Multimodal, Uncertainty-Aware Framework
  5. 2024Dr-LLaVA: Visual Instruction Tuning with Symbolic Clinical Grounding
  6. 2026Think Before You Comfort: Reflective Cognitive Alignment for Protocol-Grounded Elderly Stimulation Agents
  7. 2026Dementia-Agents: A Multi-Modal Multi-Agent System for Dementia Staging and Phenotyping
  8. 2025MMSE-Calibrated Few-Shot Prompting for Alzheimer's Detection