An LLM-based Simulation Framework for Embodied Conversational Agents in Psychological Counseling

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wu, Lixiu, Tang, Yuanrong, Pan, Qisen, Zhan, Xianyang, Han, Yucheng, Xiao, Lanxi, Wang, Tianhong, Zhong, Chen, Gong, Jiangtao
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917085052928000
author Wu, Lixiu
Tang, Yuanrong
Pan, Qisen
Zhan, Xianyang
Han, Yucheng
Xiao, Lanxi
Wang, Tianhong
Zhong, Chen
Gong, Jiangtao
author_facet Wu, Lixiu
Tang, Yuanrong
Pan, Qisen
Zhan, Xianyang
Han, Yucheng
Xiao, Lanxi
Wang, Tianhong
Zhong, Chen
Gong, Jiangtao
contents Due to privacy concerns, open dialogue datasets for mental health are primarily generated through human or AI synthesis methods. However, the inherent implicit nature of psychological processes, particularly those of clients, poses challenges to the authenticity and diversity of synthetic data. In this paper, we propose ECAs (short for Embodied Conversational Agents), a framework for embodied agent simulation based on Large Language Models (LLMs) that incorporates multiple psychological theoretical principles.Using simulation, we expand real counseling case data into a nuanced embodied cognitive memory space and generate dialogue data based on high-frequency counseling questions.We validated our framework using the D4 dataset. First, we created a public ECAs dataset through batch simulations based on D4. Licensed counselors evaluated our method, demonstrating that it significantly outperforms baselines in simulation authenticity and necessity. Additionally, two LLM-based automated evaluation methods were employed to confirm the higher quality of the generated dialogues compared to the baselines. The source code and dataset are available at https://github.com/AIR-DISCOVER/ECAs-Dataset.
format Preprint
id arxiv_https___arxiv_org_abs_2410_22041
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle An LLM-based Simulation Framework for Embodied Conversational Agents in Psychological Counseling
Wu, Lixiu
Tang, Yuanrong
Pan, Qisen
Zhan, Xianyang
Han, Yucheng
Xiao, Lanxi
Wang, Tianhong
Zhong, Chen
Gong, Jiangtao
Human-Computer Interaction
Due to privacy concerns, open dialogue datasets for mental health are primarily generated through human or AI synthesis methods. However, the inherent implicit nature of psychological processes, particularly those of clients, poses challenges to the authenticity and diversity of synthetic data. In this paper, we propose ECAs (short for Embodied Conversational Agents), a framework for embodied agent simulation based on Large Language Models (LLMs) that incorporates multiple psychological theoretical principles.Using simulation, we expand real counseling case data into a nuanced embodied cognitive memory space and generate dialogue data based on high-frequency counseling questions.We validated our framework using the D4 dataset. First, we created a public ECAs dataset through batch simulations based on D4. Licensed counselors evaluated our method, demonstrating that it significantly outperforms baselines in simulation authenticity and necessity. Additionally, two LLM-based automated evaluation methods were employed to confirm the higher quality of the generated dialogues compared to the baselines. The source code and dataset are available at https://github.com/AIR-DISCOVER/ECAs-Dataset.
title An LLM-based Simulation Framework for Embodied Conversational Agents in Psychological Counseling
topic Human-Computer Interaction
url https://arxiv.org/abs/2410.22041