paper-with-me

홈 › Papers

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

2024-07-01 · Ryan Louie, Ananjan Nandi, William Fang, Cheng Chang, Emma Brunskill, Diyi Yang

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.

📄 PDF Abstract BibTeX arXiv:2407.00870

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Attention 설명 없음
SET Dynamic Sparse Training method where weight mask is updated randomly periodically
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Multi-Head Attention 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

Similar Papers 제목 키워드 기반

Set the Stage: Enabling Storytelling with Multiple Robots through Roleplaying Metaphors

2025-08-03 · Tyrone Justin Sta Maria, Faith Griffin, Jordan Aiko Deja arxiv

Gestures are an expressive input modality for controlling multiple robots, but their use is often limited by rigid mappings and recognition constraints. To move beyond these limitations, we propose roleplaying metaphors …

Roleplaying with Structure: Synthetic Therapist-Client Conversation Generation from Questionnaires

2025-10-29 · Doan Nam Long Vu, Rui Tan, Lena Moench, Svenja Jule Francke 외 arxiv

Large Language Models (LLMs) are promising tools for synthetic data generation in mental health. However, privacy policies and restrictions forced previous work to rely mainly on generic information. We present a compreh…

Building Hierarchies of Concepts via Crowdsourcing

2015-04-27 · Yuyin Sun, Adish Singla, Dieter Fox, Andreas Krause

Hierarchies of concepts are useful in many applications from navigation to organization of objects. Usually, a hierarchy is created in a centralized manner by employing a group of domain experts, a time-consuming and exp…

The Safety Relay in Roleplay Jailbreaks: A Component-Resolved Causal Analysis of Harm Recognition and Refusal

2026-08-31 · Md Mokarram Chowdhury, Ernie Chang, Yang Li arxiv

Large language models are trained to follow instructions while refusing harmful requests. Jailbreaks exploit this balance to elicit content a model would ordinarily reject. Roleplay jailbreaks are especially concerning: …

"Many Are My Names": The Anatomy of the Assistant and Its Personas via Sparse Autoencoders

2026-08-08 · Adelaide Danilov, Aria Nourbakhsh, Oleksandr Marchenko Breneur, Salima Lamsiyah arxiv

How a language model internally represents who is speaking, the Assistant, an assigned roleplay persona, or a narrated story character, remains underexplored. We study speaker representations using a dataset of user-expr…