Cactus: Towards Psychological Counseling Conversations using Cognitive Behavioral Theory

TL;DR

Cactus introduces a realistic multi-turn dialogue dataset based on Cognitive Behavioral Therapy to improve training of language models for psychological counseling, addressing data scarcity and privacy concerns.

Contribution

We created a structured, CBT-based counseling dialogue dataset and demonstrated its effectiveness by training Camel, which outperforms other models in counseling skills.

Findings

Camel outperforms other models in counseling skills

The dataset aligns well with expert psychological criteria

Our data and models are publicly available

Abstract

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.