用三重视角建模认知扭曲，提升心理状态识别准确率
Multi-Perspective Triad Interaction Graph Neural Network for Cognitive Distortion Detection
- 将自我、世界、未来三视角融入图神经网络，捕捉心理结构
- 在4个语种数据集上达到9764样本的高精度检测，超越主流模型
- 适合心理健康分析、临床辅助诊断等应用场景
认知扭曲检测是计算心理健康的关键任务，但现有方法常忽视扭曲思维的心理结构。本文提出MTI-GNN（多视角三角互动图神经网络），将贝克的认知三元组——对自我、世界和未来的负面看法——作为互补视角用于分类。大语言模型将每条语句分解为三个视角，构建视角特定的相似性图，并由多视角图神经网络编码。三角互动模块通过序列化源条件更新和特征门控建模跨视角依赖，原型引导的视角融合实现标签条件聚合。标签扩展监督在训练中利用所有可用扭曲标注。我们在来自四个韩语、英语和中文数据集的9,764个样本上评估了MTI-GNN，涵盖十类扭曲。结果表明，该模型显著优于所有监督变体，并在零样本与少样本设置下超越八种提示生成模型。留一视角消融实验显示三个视角均贡献显著，人类专家评估也初步验证其与预期认知维度的一致性。
原文摘要 · Abstract (English)
Cognitive distortion detection is a key task in computational mental health, yet existing approaches often overlook the psychological structure of distorted thoughts. We propose MTI-GNN (Multi-Perspective Triad Interaction Graph Neural Network), which models Beck's cognitive triad---negative views of the self, world, and future---as complementary perspectives for classification. An LLM decomposes each utterance into the three perspectives, from which perspective-specific similarity graphs are constructed and encoded by a Multi-Perspective GNN. A Triad Interaction module models cross-perspective dependencies through sequential source-conditioned updates and feature-wise gating, while Prototype-Guided Perspective Fusion performs label-conditioned aggregation. Label-expanded supervision incorporates all available distortion annotations during training. We evaluate MTI-GNN on 9,764 samples from four Korean, English, and Chinese datasets spanning ten distortion categories. MTI-GNN significantly outperforms all supervised variants and exceeds eight prompted generative models under zero-shot and few-shot settings. Leave-one-perspective-out ablations show that all three perspectives contribute significantly, while human expert evaluation provides preliminary evidence of their alignment with the intended cognitive dimensions.
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。