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

arXiv: https://arxiv.org/abs/2604.12210 · HTML: https://mlsanity.com/paper/2604.12210/

## 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 (most cited first, 23 of 23)

- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Steering Llama 2 via Contrastive Activation Addition](https://mlsanity.com/paper/2312.06681/) (2023)
- [Persona Vectors: Monitoring and Controlling Character Traits in Language Models](https://mlsanity.com/paper/2507.21509/) (2025)
- [Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models](https://mlsanity.com/paper/2401.06102/) (2024)
- [Large Language Models are Superpositions of All Characters: Attaining Arbitrary Role-play via Self-Alignment](https://mlsanity.com/paper/2401.12474/) (2024)
- [Roleplay-doh: Enabling Domain-Experts to Create LLM-simulated Patients via Eliciting and Adhering to Principles](https://mlsanity.com/paper/2407.00870/) (2024)
- [Cactus: Towards Psychological Counseling Conversations using Cognitive Behavioral Theory](https://mlsanity.com/paper/2407.03103/) (2024)
- [The Oscars of AI Theater: A Survey on Role-Playing with Language Models](https://mlsanity.com/paper/2407.11484/) (2024)
- [Interactive Agents: Simulating Counselor-Client Psychological Counseling via Role-Playing LLM-to-LLM Interactions](https://mlsanity.com/paper/2408.15787/) (2024)
- [Generate, Delete and Rewrite: A Three-Stage Framework for Improving Persona Consistency of Dialogue Generation](https://mlsanity.com/paper/2004.07672/) (2020)
- [Automatic Interactive Evaluation for Large Language Models with State Aware Patient Simulator](https://mlsanity.com/paper/2403.08495/) (2024)
- [LLMs Can Simulate Standardized Patients via Agent Coevolution](https://mlsanity.com/paper/2412.11716/) (2024)
- [Leveraging Large Language Model as Simulated Patients for Clinical Education](https://mlsanity.com/paper/2404.13066/) (2024)
- [Cross-model Transferability among Large Language Models on the Platonic Representations of Concepts](https://mlsanity.com/paper/2501.02009/) (2025)
- [Improving LLM Reasoning through Interpretable Role-Playing Steering](https://mlsanity.com/paper/2506.07335/) (2025)
- [A Review of Automated Speech and Language Features for Assessment of Cognitive and Thought Disorders](https://mlsanity.com/paper/1906.01157/) (2019)
- [A Cognitive Stimulation Dialogue System with Multi-source Knowledge Fusion for Elders with Cognitive Impairment](https://mlsanity.com/paper/2305.08200/) (2023)
- [Concept -- An Evaluation Protocol on Conversational Recommender Systems with System-centric and User-centric Factors](https://mlsanity.com/paper/2404.03304/) (2024)
- [Adaptive-VP: A Framework for LLM-Based Virtual Patients that Adapts to Trainees' Dialogue to Facilitate Nurse Communication Training](https://mlsanity.com/paper/2506.00386/) (2025)
- [Modeling Challenging Patient Interactions: LLMs for Medical Communication Training](https://mlsanity.com/paper/2503.22250/) (2025)
- [Designing Role Vectors to Improve LLM Inference Behaviour](https://mlsanity.com/paper/2502.12055/) (2025)
- [A Digital Language Coherence Marker for Monitoring Dementia](https://mlsanity.com/paper/2310.09623/) (2023)
- [MedDiT: A Knowledge-Controlled Diffusion Transformer Framework for Dynamic Medical Image Generation in Virtual Simulated Patient](https://mlsanity.com/paper/2408.12236/) (2024)

## 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.