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

TL;DR

This paper introduces Roleplay-doh, a human-LLM collaboration pipeline that helps domain experts create AI-driven simulated patients for mental health training, improving adherence to expert principles and realism.

Contribution

The paper presents a novel pipeline for eliciting expert principles and integrating them into LLM roleplay, enhancing simulation fidelity and adherence to domain-specific guidelines.

Findings

30% improvement in response quality and principle adherence

Effective creation of realistic AI patients for mental health training

User study with 25 experts validates pipeline effectiveness

Abstract

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.