As mental health issues continue to rise globally, there is an increasing demand for accessible and scalable therapeutic solutions. Many individuals currently seek support from Large Language Models (LLMs), even though these models have not been validated for use in counseling services. In this paper, we evaluate LLMs' ability to emulate professional therapists practicing Cognitive Behavioral Therapy (CBT). Using anonymized, transcribed role-play sessions between licensed therapists and clients, we compare two approaches: (1) a generation-only method and (2) a Retrieval-Augmented Generation (RAG) approach using CBT guidelines. We evaluate both proprietary and open-source models for linguistic quality, semantic coherence, and therapeutic fidelity using standard natural language generation (NLG) metrics, natural language inference (NLI), and automated scoring for skills assessment. Our results indicate that while LLMs can generate CBT-like dialogues, they are limited in their ability to convey empathy and maintain consistency.
Are Large Language Models Possible to Conduct Cognitive Behavioral Therapy?
School of Information Science and Engineering, Lanzhou University（兰州大学信息科学与工程学院）；School of Medical Technology, Beijing Institute of Technology（北京理工大学医学技术学院）
AutoCBT: An Autonomous Multi-agent Framework for Cognitive Behavioral Therapy in Psychological Counseling
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；University of Chinese Academy of Sciences（中国科学院大学）；University of Science and Technology of China（中国科学技术大学）；University of Macau（澳门大学）；Shenzhen University（深圳大学）；Shenzhen MSU-BIT University（深圳北理莫斯科大学）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））
Large Language Model-Powered Conversational Agent Delivering Problem-Solving Therapy (PST) for Family Caregivers: Enhancing Empathy and Therapeutic Alliance Using In-Context Learning
Florida State University（佛罗里达州立大学）；University of Washington（华盛顿大学）；University of Texas at Austin（德克萨斯大学奥斯汀分校）
AI-Enhanced Cognitive Behavioral Therapy: Deep Learning and Large Language Models for Extracting Cognitive Pathways from Social Media Texts
School of Software Engineering, Beijing University of Technology（北京工业大学软件学院）；School of Nursing, Wuhan University（武汉大学护理学院）；Sorbonne Université, Institut du Cerveau – Paris Brain Institute - ICM, CNRS, Inria, Inserm, AP-HP, Hôpital de la Pitié-Salpêtrière（索邦大学，巴黎脑研究所-ICM，法国国家科学研究中心，法国国家信息与自动化研究所，法国国家健康与医学研究院，巴黎公共医疗集团，皮蒂-萨尔皮特里埃医院）
University of Southern California（南加州大学）；University of Pennsylvania（宾夕法尼亚大学）；University of Washington（华盛顿大学）
During a psychotherapy session, the counselor typically adopts techniques which are codified along specific dimensions (e.g., 'displays warmth and confidence', or 'attempts to set up collaboration') to facilitate the evaluation of the session. Those constructs, traditionally scored by trained human raters, reflect the complex nature of psychotherapy and highly depend on the context of the interaction. Recent advances in deep contextualized language models offer an avenue for accurate in-domain linguistic representations which can lead to robust recognition and scoring of such psychotherapy-rel…
Feel the Difference? A Comparative Analysis of Emotional Arcs in Real and LLM-Generated CBT Sessions
Department of Computer Science, Shantou University（汕头大学计算机科学系）；Department of Automation, Tsinghua University（清华大学自动化系）；BNRIST, Tsinghua University（清华大学脑科学与类脑智能研究院）
University of Denver（丹佛大学）；Eaton Senior Community（伊顿老年社区）
Social robots are becoming an integrated part of our daily life due to their ability to provide companionship and entertainment. A subfield of robotics, Socially Assistive Robotics (SAR), is particularly suitable for expanding these benefits into the healthcare setting because of its unique ability to provide cognitive, social, and emotional support. This paper presents our recent research on developing SAR by evaluating the ability of a life-like conversational social robot, called Ryan, to administer internet-delivered cognitive behavioral therapy (iCBT) to older adults with depression. For …
CBT-Bench: Evaluating Large Language Models on Assisting Cognitive Behavior Therapy
The University of Texas at Dallas（德克萨斯大学达拉斯分校）；University of California, Santa Barbara（加利福尼亚大学圣巴巴拉分校）；University of Pittsburgh（匹兹堡大学）；Princeton University（普林斯顿大学）；Carnegie Mellon University（卡内基梅隆大学）
University of Southern California（南加州大学）；University of Pennsylvania（宾夕法尼亚大学）；University of Washington（华盛顿大学）
In order to increase mental health equity among the most vulnerable and marginalized communities, it is important to increase access to high-quality therapists. One facet of addressing these needs, is to provide timely feedback to clinicians as they interact with their clients, in a way that is also contextualized to specific clients and interactions they have had. Dynamical systems provide a framework through which to analyze interactions. The present work applies these methods to the domain of automated psychotherapist evaluation for Cognitive Behavioral Therapy (CBT). Our methods extract lo…
The Thinking Therapist: Training Large Language Models to Deliver Acceptance and Commitment Therapy using Supervised Fine-Tuning and Odds Ratio Policy Optimization
Department of Psychiatry University of Toronto（精神病学系多伦多大学）
The Art of Socratic Inquiry: A Framework for Proactive Template-Guided Therapeutic Conversation Generation
School of Information Science and Engineering, Lanzhou University（信息科学与工程学院，兰州大学）；School of Medical Technology, Beijing Institute of Technology（医学技术学院，北京理工大学）
University of Cambridge（剑桥大学）；CM Insight；Imperial College London（帝国理工学院）
In recent years, we have seen deep learning and distributed representations of words and sentences make impact on a number of natural language processing tasks, such as similarity, entailment and sentiment analysis. Here we introduce a new task: understanding of mental health concepts derived from Cognitive Behavioural Therapy (CBT). We define a mental health ontology based on the CBT principles, annotate a large corpus where this phenomena is exhibited and perform understanding using deep learning and distributed representations. Our results show that the performance of deep learning models c…
University of Southern California（南加州大学）；University of Pennsylvania（宾夕法尼亚大学）；University of Utah（犹他大学）；University of Washington（华盛顿大学）
Cognitive Behavioral Therapy (CBT) is a goal-oriented psychotherapy for mental health concerns implemented in a conversational setting with broad empirical support for its effectiveness across a range of presenting problems and client populations. The quality of a CBT session is typically assessed by trained human raters who manually assign pre-defined session-level behavioral codes. In this paper, we develop an end-to-end pipeline that converts speech audio to diarized and transcribed text and extracts linguistic features to code the CBT sessions automatically. We investigate both word-level …
University of Southern California（南加州大学）；Interactions LLC（Interactions有限责任公司）；University of Pennsylvania（宾夕法尼亚大学）；University of Washington（华盛顿大学）
Text-based computational approaches for assessing the quality of psychotherapy are being developed to support quality assurance and clinical training. However, due to the long durations of typical conversation based therapy sessions, and due to limited annotated modeling resources, computational methods largely rely on frequency-based lexical features or dialogue acts to assess the overall session level characteristics. In this work, we propose a hierarchical framework to automatically evaluate the quality of transcribed Cognitive Behavioral Therapy (CBT) interactions. Given the richly dynamic…
DiaCBT: A Long-Periodic Dialogue Corpus Guided by Cognitive Conceptualization Diagram for CBT-based Psychological Counseling
Shanghai Institute of Artificial Intelligence for Education, East China Normal University（上海教育人工智能研究院，东华师范大学）；School of Computer Science and Technology, East China Normal University（计算机科学与技术学院，东华师范大学）；School of Psychology and Cognitive Science, East China Normal University（心理学与认知科学学院，东华师范大学）
Tsinghua University（清华大学）；Beijing Normal University（北京师范大学）
The growing demand for mental health support has highlighted the importance of conversational agents as human supporters worldwide and in China. These agents could increase availability and reduce the relative costs of mental health support. The provided support can be divided into two main types: cognitive and emotional support. Existing work on this topic mainly focuses on constructing agents that adopt Cognitive Behavioral Therapy (CBT) principles. Such agents operate based on pre-defined templates and exercises to provide cognitive support. However, research on emotional support using such…
