基于大语言模型的认知行为疗法回复生成：与苏格拉底式提问的对比研究
Response Generation for Cognitive Behavioral Therapy with Large Language Models: Comparative Study with Socratic Questioning
AI总结：
本研究对比基于OsakaED数据集训练的Transformer对话模型与GPT-4在苏格拉底式提问CBT对话场景中的表现，发现GPT-4可显著提升情绪改善与对话质量，同时指出LLM可辅助专业人员制作回复模板以规避直接应用的伦理风险。
摘要：
由源自咨询技术（如认知行为疗法，即CBT）的预定义或基于规则的场景所控制的对话系统，在心理健康类应用中发挥着重要作用。尽管需要负责任的回复，但可以想见，利用新兴的大语言模型（LLM）生成与语境相关的话语将提升这类应用的效用。本研究围绕传统苏格拉底式提问的CBT场景构建对话模块，采用两种大语言模型：一种是基于Transformer的对话模型，使用大阪府提供的社交媒体共情咨询数据集（OsakaED）进一步训练；另一种是OpenAI开发的前沿大语言模型GPT-4。通过对比使用LLM生成回复的系统与不使用该类回复的系统，我们探究了生成式回复对情绪变化、认知变化以及对话质量（如同理心）等主观评估指标的影响。结果显示，使用OsakaED模型时未观察到显著提升。而使用GPT-4时，情绪变化幅度、同理心及其他对话质量均有显著改善。研究结果表明GPT-4具备较高的咨询能力，但同时也指出，即便使用经人类咨询数据集训练的对话模型，其效果也未必优于基于场景的对话。虽然直接呈现包括GPT-4在内的LLM生成回复并让其在现实心理健康服务中与用户直接互动可能引发伦理问题，但在使用规则、场景或示例回复的系统中，人类专业人员仍可提前借助LLM制作示例回复或回复模板。
英文摘要：
Dialogue systems controlled by predefined or rule-based scenarios derived from counseling techniques, such as cognitive behavioral therapy (CBT), play an important role in mental health apps. Despite the need for responsible responses, it is conceivable that using the newly emerging LLMs to generate contextually relevant utterances will enhance these apps. In this study, we construct dialogue modules based on a CBT scenario focused on conventional Socratic questioning using two kinds of LLMs: a Transformer-based dialogue model further trained with a social media empathetic counseling dataset, provided by Osaka Prefecture (OsakaED), and GPT-4, a state-of-the art LLM created by OpenAI. By comparing systems that use LLM-generated responses with those that do not, we investigate the impact of generated responses on subjective evaluations such as mood change, cognitive change, and dialogue quality (e.g., empathy). As a result, no notable improvements are observed when using the OsakaED model. When using GPT-4, the amount of mood change, empathy, and other dialogue qualities improve significantly. Results suggest that GPT-4 possesses a high counseling ability. However, they also indicate that even when using a dialogue model trained with a human counseling dataset, it does not necessarily yield better outcomes compared to scenario-based dialogues. While presenting LLM-generated responses, including GPT-4, and having them interact directly with users in real-life mental health care services may raise ethical issues, it is still possible for human professionals to produce example responses or response templates using LLMs in advance in systems that use rules, scenarios, or example responses.
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。
