Cactus: Towards Psychological Counseling Conversations using Cognitive Behavioral Theory

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 is necessary, but this approach faces a key challenge: the absence of realistic counseling datasets. To address the issue of dataset scarcity, 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 (1) designing clients with varied, specific personas, and (2) 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 human 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 dataset, model, and code publicly available. 1 * Equal contribution 1 https://github.com/coding-groot/cactus