用认知策略提升LLM识别并干预情绪对话中的思维扭曲。
Cognitive Policy-Driven LLM for Diagnosis and Intervention of Cognitive Distortions in Emotional Support Conversation
- 构建认知扭曲标注数据集CogBiasESC，含类型、强度与安全风险标签。
- 提出CoPoLLM框架，诊断准确率与干预效果优于15个主流模型。
- 适合心理支持、AI助医等需深度认知干预的场景使用。
情感支持对话（ESC）在心理健康辅助中至关重要，能为现实应用提供可及的心理支持。大型语言模型（LLMs）在ESC任务中展现出强大的共情能力，但现有方法忽视了求助者表达中的认知扭曲问题。因此，当前模型仅能提供基础情绪安慰，无法从深层认知层面帮助缓解心理困扰。为此，我们构建了首个扩展现有ESC数据集的认知扭曲标注数据集CogBiasESC，包含扭曲类型、强度及安全风险等级标签。同时，提出认知策略驱动的大型语言模型框架（CoPoLLM），以增强模型对认知扭曲的诊断与干预能力。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个先进基线模型。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。