Enhancing Psychotherapeutic Alliance in College: When and How to Integrate Multimodal Large Language Models in Psychotherapy

2025-02-01

AI Summary

Low user acceptance, strong privacy concerns, and insufficient personalization hinder the safe and effective integration of multimodal large language models (MLLMs) in university psychological counseling—where MLLMs should augment, not replace, human counselors. Method: A three-phase mixed-methods study was conducted: (1) needs assessment via surveys and interviews; (2) situated usability testing with real-time multimodal emotion recognition; and (3) human-AI collaboration analysis. Contribution/Results: We propose the “therapist-augmenting” paradigm, identifying social identification and perceived relative status of MLLMs as key psychological determinants of acceptance. Triage matching and real-time emotional support emerged as highest-priority functionalities, while capability credibility and privacy-ethics trade-offs constitute primary barriers to autonomous MLLM interventions. This work delivers the first empirically grounded, ethics-technology co-design framework for intelligent campus mental health systems.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

As mental health issues rise among college students, there is an increasing interest and demand in leveraging Multimodal Language Models (MLLM) to enhance mental support services, yet integrating them into psychotherapy remains theoretical or non-user-centered. This study investigated the opportunities and challenges of using MLLMs within the campus psychotherapy alliance in China. Through three studies involving both therapists and student clients, we argue that the ideal role for MLLMs at this stage is as an auxiliary tool to human therapists. Users widely expect features such as triage matching and real-time emotion recognition. At the same time, for independent therapy by MLLM, concerns about capabilities and privacy ethics remain prominent, despite high demands for personalized avatars and non-verbal communication. Our findings further indicate that users' sense of social identity and perceived relative status of MLLMs significantly influence their acceptance. This study provides insights for future intelligent campus mental healthcare.

Problem

• Multimodal Large Language Models
• University Psychological Counseling
• Privacy Protection and Personalization

Innovation

• Multimodal Language Models
• Psychological Counseling
• Personalized Therapy