COCOA: CBT-based Conversational Counseling Agent using Memory Specialized in Cognitive Distortions and Dynamic Prompt
This work addresses the need for automated mental health counseling agents, but it appears incremental as it builds on existing CBT methods with specialized memory and prompting.
The authors tackled the problem of creating a conversational agent for mental health care by developing CoCoA, which uses CBT techniques to identify and address cognitive distortions in client statements, and it demonstrated a statistically significant difference from other models in evaluations.
The demand for conversational agents that provide mental health care is consistently increasing. In this work, we develop a psychological counseling agent, referred to as CoCoA, that applies Cognitive Behavioral Therapy (CBT) techniques to identify and address cognitive distortions inherent in the client's statements. Specifically, we construct a memory system to efficiently manage information necessary for counseling while extracting high-level insights about the client from their utterances. Additionally, to ensure that the counseling agent generates appropriate responses, we introduce dynamic prompting to flexibly apply CBT techniques and facilitate the appropriate retrieval of information. We conducted dialogues between CoCoA and characters from Character.ai, creating a dataset for evaluation. Then, we asked GPT to evaluate the constructed counseling dataset, and our model demonstrated a statistically significant difference from other models.