CPsyCoun: A Report-based Multi-turn Dialogue Reconstruction and Evaluation Framework for Chinese Psychological Counseling

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Chenhao, Li, Renhao, Tan, Minghuan, Yang, Min, Zhu, Jingwei, Yang, Di, Zhao, Jiahao, Ye, Guancheng, Li, Chengming, Hu, Xiping
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917689116590080
author Zhang, Chenhao
Li, Renhao
Tan, Minghuan
Yang, Min
Zhu, Jingwei
Yang, Di
Zhao, Jiahao
Ye, Guancheng
Li, Chengming
Hu, Xiping
author_facet Zhang, Chenhao
Li, Renhao
Tan, Minghuan
Yang, Min
Zhu, Jingwei
Yang, Di
Zhao, Jiahao
Ye, Guancheng
Li, Chengming
Hu, Xiping
contents Using large language models (LLMs) to assist psychological counseling is a significant but challenging task at present. Attempts have been made on improving empathetic conversations or acting as effective assistants in the treatment with LLMs. However, the existing datasets lack consulting knowledge, resulting in LLMs lacking professional consulting competence. Moreover, how to automatically evaluate multi-turn dialogues within the counseling process remains an understudied area. To bridge the gap, we propose CPsyCoun, a report-based multi-turn dialogue reconstruction and evaluation framework for Chinese psychological counseling. To fully exploit psychological counseling reports, a two-phase approach is devised to construct high-quality dialogues while a comprehensive evaluation benchmark is developed for the effective automatic evaluation of multi-turn psychological consultations. Competitive experimental results demonstrate the effectiveness of our proposed framework in psychological counseling. We open-source the datasets and model for future research at https://github.com/CAS-SIAT-XinHai/CPsyCoun
format Preprint
id arxiv_https___arxiv_org_abs_2405_16433
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle CPsyCoun: A Report-based Multi-turn Dialogue Reconstruction and Evaluation Framework for Chinese Psychological Counseling
Zhang, Chenhao
Li, Renhao
Tan, Minghuan
Yang, Min
Zhu, Jingwei
Yang, Di
Zhao, Jiahao
Ye, Guancheng
Li, Chengming
Hu, Xiping
Computation and Language
Artificial Intelligence
Computers and Society
Using large language models (LLMs) to assist psychological counseling is a significant but challenging task at present. Attempts have been made on improving empathetic conversations or acting as effective assistants in the treatment with LLMs. However, the existing datasets lack consulting knowledge, resulting in LLMs lacking professional consulting competence. Moreover, how to automatically evaluate multi-turn dialogues within the counseling process remains an understudied area. To bridge the gap, we propose CPsyCoun, a report-based multi-turn dialogue reconstruction and evaluation framework for Chinese psychological counseling. To fully exploit psychological counseling reports, a two-phase approach is devised to construct high-quality dialogues while a comprehensive evaluation benchmark is developed for the effective automatic evaluation of multi-turn psychological consultations. Competitive experimental results demonstrate the effectiveness of our proposed framework in psychological counseling. We open-source the datasets and model for future research at https://github.com/CAS-SIAT-XinHai/CPsyCoun
title CPsyCoun: A Report-based Multi-turn Dialogue Reconstruction and Evaluation Framework for Chinese Psychological Counseling
topic Computation and Language
Artificial Intelligence
Computers and Society
url https://arxiv.org/abs/2405.16433