认知驱动的LLM用于情绪支持对话中认知扭曲的诊断与干预
Cognitive Policy-Driven LLM for Diagnosis and Intervention of Cognitive Distortions in Emotional Support Conversation
AI总结：
本文提出CogBiasESC数据集和CoPoLLM框架，用于提升LLM在情绪支持对话中识别和干预认知扭曲的能力，实验显示其在诊断准确性和安全性方面优于现有方法。
摘要：
情绪支持对话（ESC）在心理健康援助中起着关键作用，通过提供现实世界中的心理支持。大型语言模型（LLMs）在ESC任务中展示了强大的同理心能力。然而，现有方法忽视了求助者表达中的认知扭曲问题。为此，我们构建了CogBiasESC数据集，这是首个扩展现有ESC数据集并添加认知扭曲标签的数据集，包括其类型、强度和安全风险等级。此外，我们提出了认知政策驱动的大型语言模型框架（CoPoLLM），以增强LLM在识别和干预求助者认知扭曲方面的能力。我们还从理论角度分析了CoPoLLM的安全优势。实验结果表明，CoPoLLM在认知扭曲诊断准确率、干预策略有效性及安全风险控制方面显著优于15种最先进的基线方法。
英文摘要：
Emotional Support Conversation (ESC) plays a critical role in mental health assistance by providing accessible psychological support in real-world applications. Large Language Models (LLMs) have shown strong empathetic abilities in ESC tasks. Yet, existing methods overlook the issue of cognitive distortions in help-seekers' expressions. As a result, current models can only provide basic emotional comfort, rather than helping help-seekers address their psychological distress at a deeper cognitive level. To address this challenge, we construct the CogBiasESC dataset, the first dataset that expands existing ESC datasets by adding labels for cognitive distortions, includes their type, intensity, and safe risk level. Furthermore, we propose the Cognitive Policy-driven Large Language Model framework (CoPoLLM) to enhance LLMs' ability to diagnose and intervene cognitive distortions in help-seekers. We also analyze the safety advantages of CoPoLLM from a theoretical perspective. Experimental results show that CoPoLLM significantly outperforms 15 state-of-the-art baselines in terms of distortion diagnosis accuracy, intervention strategy effectiveness, and safety risk control.
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。
