发表机构
Monash University; University of Liverpool; Massachusetts Institute of Technology; The University of Melbourne; Orygen（莫纳什大学; 利物浦大学; 麻省理工学院; 墨尔本大学; 奥里根）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出StratCBT数据集，包含9,688个会话和约256K条话语，将咨询师回应与八种CBT策略对齐，通过自我对话生成高质量对话，显著提升咨询效果。
AI 中文摘要
大型语言模型的最新进展彻底改变了心理咨询领域，尤其是在认知行为疗法（CBT）的背景下。虽然CBT的成功在很大程度上依赖于根据客户实时心理状态进行的动态决策，但这一方面在当前研究中常常被忽视，限制了灵活性和治疗效果。在本文中，我们介绍了StratCBT，一个专门为带有CBT策略的心理咨询对话设计的数据集，包含9,688个会话和约256K条话语，每位咨询师的回应与八种不同策略之一对齐。StratCBT的创建涉及基于客户的消极思维对客户进行建模，并通过自我对话生成高质量的心理咨询对话，结合真实会话作为指导，从而在一般咨询和CBT特定技能方面显著超越现有数据集。我们进行了大量实验，以证明策略对齐生成的有效性，并评估其在LLM模拟客户场景中提供专业有效咨询的效能，以反映现实世界的情况。该数据集可通过此https URL获取。
英文摘要
Recent advancements in large language models have revolutionized the field of psychological counseling, especially in the context of Cognitive Behavioral Therapy (CBT). While the success of CBT relies heavily on dynamic decision-making informed by the client's real-time mental state, this aspect has often been overlooked in current research, limiting both flexibility and therapeutic outcomes. In this paper, we introduce StratCBT, a dataset specifically designed for psychological counseling conversations with CBT Strategies, consisting of 9,688 sessions and around 256K utterances, with each counselor's response aligned with one of eight distinct strategies. The creation of StratCBT involves modeling clients based on their negative thoughts and generating high-quality counseling conversations through self-chat, incorporating realistic sessions as guidance, thereby significantly surpassing existing datasets in both general counseling and CBT-specific skills. We conduct extensive experiments to demonstrate the effectiveness of strategy-aligned generation and evaluate its efficacy in delivering professional and effective counseling with LLM-simulated clients to reflect real-world scenarios. The dataset can be obtained from https://github.com/zimuwangnlp/StratCBT.
CommentsAccepted at EMNLP 2026
