Saved in:
Bibliographic Details
Main Authors: Lee, Suyeon, Kim, Sunghwan, Kim, Minju, Kang, Dongjin, Yang, Dongil, Kim, Harim, Kang, Minseok, Jung, Dayi, Kim, Min Hee, Lee, Seungbeen, Chung, Kyoung-Mee, Yu, Youngjae, Lee, Dongha, Yeo, Jinyoung
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.03103
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916424305344512
author Lee, Suyeon
Kim, Sunghwan
Kim, Minju
Kang, Dongjin
Yang, Dongil
Kim, Harim
Kang, Minseok
Jung, Dayi
Kim, Min Hee
Lee, Seungbeen
Chung, Kyoung-Mee
Yu, Youngjae
Lee, Dongha
Yeo, Jinyoung
author_facet Lee, Suyeon
Kim, Sunghwan
Kim, Minju
Kang, Dongjin
Yang, Dongil
Kim, Harim
Kang, Minseok
Jung, Dayi
Kim, Min Hee
Lee, Seungbeen
Chung, Kyoung-Mee
Yu, Youngjae
Lee, Dongha
Yeo, Jinyoung
contents Recently, the demand for psychological counseling has significantly increased as more individuals express concerns about their mental health. This surge has accelerated efforts to improve the accessibility of counseling by using large language models (LLMs) as counselors. To ensure client privacy, training open-source LLMs faces a key challenge: the absence of realistic counseling datasets. To address this, we introduce Cactus, a multi-turn dialogue dataset that emulates real-life interactions using the goal-oriented and structured approach of Cognitive Behavioral Therapy (CBT). We create a diverse and realistic dataset by designing clients with varied, specific personas, and having counselors systematically apply CBT techniques in their interactions. To assess the quality of our data, we benchmark against established psychological criteria used to evaluate real counseling sessions, ensuring alignment with expert evaluations. Experimental results demonstrate that Camel, a model trained with Cactus, outperforms other models in counseling skills, highlighting its effectiveness and potential as a counseling agent. We make our data, model, and code publicly available.
format Preprint
id arxiv_https___arxiv_org_abs_2407_03103
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Cactus: Towards Psychological Counseling Conversations using Cognitive Behavioral Theory
Lee, Suyeon
Kim, Sunghwan
Kim, Minju
Kang, Dongjin
Yang, Dongil
Kim, Harim
Kang, Minseok
Jung, Dayi
Kim, Min Hee
Lee, Seungbeen
Chung, Kyoung-Mee
Yu, Youngjae
Lee, Dongha
Yeo, Jinyoung
Computation and Language
Recently, the demand for psychological counseling has significantly increased as more individuals express concerns about their mental health. This surge has accelerated efforts to improve the accessibility of counseling by using large language models (LLMs) as counselors. To ensure client privacy, training open-source LLMs faces a key challenge: the absence of realistic counseling datasets. To address this, we introduce Cactus, a multi-turn dialogue dataset that emulates real-life interactions using the goal-oriented and structured approach of Cognitive Behavioral Therapy (CBT). We create a diverse and realistic dataset by designing clients with varied, specific personas, and having counselors systematically apply CBT techniques in their interactions. To assess the quality of our data, we benchmark against established psychological criteria used to evaluate real counseling sessions, ensuring alignment with expert evaluations. Experimental results demonstrate that Camel, a model trained with Cactus, outperforms other models in counseling skills, highlighting its effectiveness and potential as a counseling agent. We make our data, model, and code publicly available.
title Cactus: Towards Psychological Counseling Conversations using Cognitive Behavioral Theory
topic Computation and Language
url https://arxiv.org/abs/2407.03103