感知差异？真实与LLM生成CBT对话中情感弧的比较分析
Feel the Difference? A Comparative Analysis of Emotional Arcs in Real and LLM-Generated CBT Sessions
AI总结：
本研究通过比较真实与LLM生成的CBT对话，揭示了合成对话在情感动态上的不足，强调了情感真实性的关键作用。
摘要：
由大型语言模型（LLM）生成的合成治疗对话越来越多地用于心理健康NLP领域，以模拟咨询场景、训练模型并补充有限的现实数据。然而，仍然不清楚这些合成对话是否能捕捉到真实治疗中细腻的情感动态。在本工作中，我们引入了真实CBT对话的真实数据集（RealCBT），并进行了首次真实与LLM生成CBT对话之间情感弧的比较分析。我们适应了话语情感动态框架，以分析在效价、唤醒和主导性维度上细粒度的情感轨迹。我们的分析涵盖了完整的对话和个体说话者角色（咨询师和来访者），使用来自RealCBT数据集的真实对话和来自CACTUS数据集的合成对话。我们发现，尽管合成对话流畅且结构上一致，但在关键情感属性上与真实对话存在差异：真实对话表现出更高的情感变异性、更多情感丰富的语言以及更真实的反应和调节模式。此外，情感弧相似性在所有配对中都较低，尤其是真实与合成说话者之间的匹配尤其薄弱。这些发现突显了当前LLM生成治疗数据的局限性，并强调了心理健康应用中情感真实性的的重要性。为了支持未来研究，我们的数据集RealCBT在https://gitlab.com/xiaoyi.wang/realcbt-dataset上发布。
英文摘要：
Synthetic therapy dialogues generated by large language models (LLMs) are increasingly used in mental health NLP to simulate counseling scenarios, train models, and supplement limited real-world data. However, it remains unclear whether these synthetic conversations capture the nuanced emotional dynamics of real therapy. In this work, we introduce RealCBT, a dataset of authentic cognitive behavioral therapy (CBT) dialogues, and conduct the first comparative analysis of emotional arcs between real and LLM-generated CBT sessions. We adapt the Utterance Emotion Dynamics framework to analyze fine-grained affective trajectories across valence, arousal, and dominance dimensions. Our analysis spans both full dialogues and individual speaker roles (counselor and client), using real sessions from the RealCBT dataset and synthetic dialogues from the CACTUS dataset. We find that while synthetic dialogues are fluent and structurally coherent, they diverge from real conversations in key emotional properties: real sessions exhibit greater emotional variability, more emotion-laden language, and more authentic patterns of reactivity and regulation. Moreover, emotional arc similarity remains low across all pairings, with especially weak alignment between real and synthetic speakers. These findings underscore the limitations of current LLM-generated therapy data and highlight the importance of emotional fidelity in mental health applications. To support future research, our dataset RealCBT is released at https://gitlab.com/xiaoyi.wang/realcbt-dataset.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
