MIRROR: Multimodal Cognitive Reframing Therapy for Rolling with Resistance
This addresses the issue of weakened therapeutic alliance in AI psychotherapy for clients, though it is incremental as it builds on existing LLM-based CBT with added multimodal features.
The paper tackled the problem of client resistance in AI-based psychotherapy by proposing a multimodal approach that incorporates nonverbal facial cues, resulting in significant enhancement of the AI therapist's ability to handle resistance and outperform existing text-based methods.
Recent studies have explored the use of large language models (LLMs) in psychotherapy; however, text-based cognitive behavioral therapy (CBT) models often struggle with client resistance, which can weaken therapeutic alliance. To address this, we propose a multimodal approach that incorporates nonverbal cues, which allows the AI therapist to better align its responses with the client's negative emotional state. Specifically, we introduce a new synthetic dataset, Mirror (Multimodal Interactive Rolling with Resistance), which is a novel synthetic dataset that pairs each client's statements with corresponding facial images. Using this dataset, we train baseline vision language models (VLMs) so that they can analyze facial cues, infer emotions, and generate empathetic responses to effectively manage client resistance. These models are then evaluated in terms of both their counseling skills as a therapist, and the strength of therapeutic alliance in the presence of client resistance. Our results demonstrate that Mirror significantly enhances the AI therapist's ability to handle resistance, which outperforms existing text-based CBT approaches. Human expert evaluations further confirm the effectiveness of our approach in managing client resistance and fostering therapeutic alliance.