mlsanityData to 14 Oct 2026

Roleplay-doh: Enabling Domain-Experts to Create LLM-simulated Patients via Eliciting and Adhering to Principles

arXiv 2407.00870 ↗First posted 1 Jul 2024cs.CL cs.HCcited by 73

Not on the map. Why?

Abstract (arXiv)

Recent works leverage LLMs to roleplay realistic social scenarios, aiding novices in practicing their social skills. However, simulating sensitive interactions, such as in mental health, is challenging. Privacy concerns restrict data access, and collecting expert feedback, although vital, is laborious. To address this, we develop Roleplay-doh, a novel human-LLM collaboration pipeline that elicits qualitative feedback from a domain-expert, which is transformed into a set of principles, or natural language rules, that govern an LLM-prompted roleplay. We apply this pipeline to enable senior mental health supporters to create customized AI patients for simulated practice partners for novice counselors. After uncovering issues in GPT-4 simulations not adhering to expert-defined principles, we also introduce a novel principle-adherence prompting pipeline which shows 30% improvements in response quality and principle following for the downstream task. Via a user study with 25 counseling experts, we demonstrate that the pipeline makes it easy and effective to create AI patients that more faithfully resemble real patients, as judged by creators and third-party counselors. See our project website at https://roleplay-doh.github.io/ for code and data.

Key facts. Cited by 73 papers in the map (data through 14 Oct 2026). Builds on 17 of its 70 references that are in the map. First posted on arXiv 1 Jul 2024.

Builds on

17 of 70 references.

References · 17

  1. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  2. 2017Deep reinforcement learning from human preferencescited by 3,912
  3. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  4. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  5. 2022Constitutional AI: Harmlessness from AI Feedbackcited by 3,050
  6. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,592
  7. 2022Social Simulacra: Creating Populated Prototypes for Social Computing Systemscited by 301
  8. 2021Towards Emotional Support Dialog Systemscited by 299
  9. 2023Branch-Solve-Merge Improves Large Language Model Evaluation and Generationcited by 106
  10. 2023CoMPosT: Characterizing and Evaluating Caricature in LLM Simulationscited by 97
  11. 2023EvalLM: Interactive Evaluation of Large Language Model Prompts on User-Defined Criteriacited by 74
  12. 2023COLLIE: Systematic Construction of Constrained Text Generation Taskscited by 70
5 more
  1. 2024Is this the real life? Is this just fantasy? The Misleading Success of Simulating Social Interactions With LLMscited by 59
  2. 2023ConstitutionMaker: Interactively Critiquing Large Language Models by Converting Feedback into Principlescited by 33
  3. 2022When Life Gives You Lemons, Make Cherryade: Converting Feedback from Bad Responses into Good Labelscited by 20
  4. 2021Goldilocks: Consistent Crowdsourced Scalar Annotations with Relative Uncertaintycited by 12
  5. 2023Seeing Seeds Beyond Weeds: Green Teaming Generative AI for Beneficial Usescited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 13; 2025: 34; 2026: 26.

73 papers.

Sort:

By area:

  1. 2024Programming Refusal with Conditional Activation Steeringcited by 206
  2. 2024PersonaGym: Evaluating Persona Agents and LLMscited by 97
  3. 2025Expressing stigma and inappropriate responses prevents LLMs from safely replacing mental health providerscited by 69
  4. 2025PatientSim: A Persona-Driven Simulator for Realistic Doctor-Patient Interactionscited by 32
  5. 2024'Simulacrum of Stories': Examining Large Language Models as Qualitative Research Participantscited by 28
  6. 2025Multi-turn Evaluation of Anthropomorphic Behaviours in Large Language Modelscited by 25
  7. 2024What Should We Engineer in Prompts? Training Humans in Requirement-Driven LLM Usecited by 24
  8. 2024LLMs Can Simulate Standardized Patients via Agent Coevolutioncited by 22
  9. 2025EmoAgent: Assessing and Safeguarding Human-AI Interaction for Mental Health Safetycited by 21
  10. 2025Sentient Agent as a Judge: Evaluating Higher-Order Social Cognition in Large Language Modelscited by 21
  11. 2025Cultural Learning-Based Culture Adaptation of Language Modelscited by 16
  12. 2025PRINCIPLES: Synthetic Strategy Memory for Proactive Dialogue Agentscited by 15
38 more
  1. 2025Scaffolding Empathy: Training Counselors with Simulated Patients and Utterance-level Performance Visualizationscited by 14
  2. 2024Simulated patient systems powered by large language model-based AI agents offer potential for transforming medical educationcited by 13
  3. 2024CBT-Bench: Evaluating Large Language Models on Assisting Cognitive Behavior Therapycited by 12
  4. 2025A Survey of Large Language Models in Psychotherapy: Current Landscape and Future Directionscited by 12
  5. 2024Fairness Testing of Large Language Models in Role-Playingcited by 11
  6. 2025Crisp: Cognitive Restructuring of Negative Thoughts through Multi-turn Supportive Dialoguescited by 11
  7. 2024PingPong: A Benchmark for Role-Playing Language Models with User Emulation and Multi-Model Evaluationcited by 10
  8. 2025Adaptive-VP: A Framework for LLM-Based Virtual Patients that Adapts to Trainees' Dialogue to Facilitate Nurse Communication Trainingcited by 9
  9. 2026The Chameleon's Limit: Investigating Persona Collapse and Homogenization in Large Language Modelscited by 8
  10. 2025Modeling Challenging Patient Interactions: LLMs for Medical Communication Trainingcited by 7
  11. 2024PersLLM: A Personified Training Approach for Large Language Modelscited by 6
  12. 2025HamRaz: A Culture-Based Persian Conversation Dataset for Person-Centered Therapy Using LLM Agentscited by 6
  13. 2025Do Role-Playing Agents Practice What They Preach? Belief-Behavior Consistency in LLM-Based Simulations of Human Trustcited by 6
  14. 2025TalkDep: Clinically Grounded LLM Personas for Conversation-Centric Depression Screeningcited by 6
  15. 2025Harmful Traits of AI Companionscited by 6
  16. 2025ChatThero: An LLM-Supported Chatbot for Behavior Change and Therapeutic Support in Addiction Recoverycited by 4
  17. 2026PatientHub: A Unified Framework for Patient Simulationcited by 4
  18. 2025CueTip: An Interactive and Explainable Physics-aware Pool Assistantcited by 3
  19. 2025Eeyore: Realistic Depression Simulation via Supervised and Preference Optimizationcited by 3
  20. 2025TN-Eval: Rubric and Evaluation Protocols for Measuring the Quality of Behavioral Therapy Notescited by 3
  21. 2025TRUST: An LLM-Based Dialogue System for Trauma Understanding and Structured Assessmentscited by 3
  22. 2025Reframe Your Life Story: Interactive Narrative Therapist and Innovative Moment Assessment with Large Language Modelscited by 3
  23. 2026CALM-IT: Enhancing Synthetic Motivational Interviewing Dialogue Quality with Conversational Dynamicscited by 3
  24. 2026Assessing Risks of Large Language Models in Mental Health Support: A Framework for Automated Clinical AI Red Teamingcited by 3
  25. 2026AI generates well-liked but templatic empathic responsescited by 3
  26. 2024Inertia in Moral and Value Judgments of Large Language Modelscited by 2
  27. 2025MedSimAI: Simulation and Formative Feedback Generation to Enhance Deliberate Practice in Medical Educationcited by 2
  28. 2025Patient-Zero: Scaling Synthetic Patient Agents to Real-World Distributions without Real Patient Datacited by 2
  29. 2026Responsible Evaluation of AI for Mental Healthcited by 2
  30. 2026METRO: Towards Strategy Induction from Expert Dialogue Transcripts for Non-collaborative Dialoguescited by 2
  31. 2026PSI-Bench: Interpretable and Clinically Meaningful Evaluation of Depression Patient Simulatorscited by 2
  32. 2024MentalArena: Self-play Training of Language Models for Diagnosis and Treatment of Mental Health Disorderscited by 1
  33. 2025Free Lunch for User Experience: Crowdsourcing Agents for Scalable User Studiescited by 1
  34. 2025A Similarity Measure for Comparing Conversational Dynamicscited by 1
  35. 2025Botender: Supporting Communities in Collaboratively Designing AI Agents through Case-Based Provocationscited by 1
  36. 2025PrimeX: A Dataset of Worldview, Opinion, and Explanationcited by 1
  37. 2026HAL: Inducing Human-likeness in LLMs with Alignmentcited by 1
  38. 2026PsyCLIENT: Client Simulation via Conversational Trajectory Modeling for Trainee Practice and Model Evaluation in Mental Health Counselingcited by 1

50 most cited of 73 All 73 (JSON)