用大模型增强多视图注意力，提升心理扭曲检测的可解释性。
Multi-View Attention Multiple-Instance Learning Enhanced by LLM Reasoning for Cognitive Distortion Detection
- 将话语拆解为情绪、逻辑、行为三部分，由大模型推理扭曲实例。
- 在韩英双语数据集上，准确率显著提升，尤其对模糊扭曲有效。
- 适合心理健康NLP研究者，提供可解释的细粒度分析方法。
认知扭曲与心理健康障碍密切相关，但其自动检测因上下文模糊、共现及语义重叠而困难。本文提出一种结合大语言模型（LLM）与多实例学习（MIL）的新框架，提升可解释性与表达层面推理能力。每个话语被分解为情绪、逻辑、行为（ELB）三部分，由大模型推断多个扭曲实例，每例包含预测类型、表达形式及模型赋予的显著性得分。这些实例通过多视图门控注意力机制融合，完成最终分类。在韩语（KoACD）和英语（Therapist QA）数据集上的实验表明，引入ELB结构和大模型推导的显著性得分能有效提升分类性能，尤其在高解释模糊性的扭曲检测中表现突出。结果表明该方法具有心理学基础且具备良好泛化能力，适用于细粒度心理状态分析。数据集与实现代码已公开。
原文摘要 · Abstract (English)
Cognitive distortions have been closely linked to mental health disorders, yet their automatic detection remains challenging due to contextual ambiguity, co-occurrence, and semantic overlap. We propose a novel framework that combines Large Language Models (LLMs) with a Multiple-Instance Learning (MIL) architecture to enhance interpretability and expression-level reasoning. Each utterance is decomposed into Emotion, Logic, and Behavior (ELB) components, which are processed by LLMs to infer multiple distortion instances, each with a predicted type, expression, and model-assigned salience score. These instances are integrated via a Multi-View Gated Attention mechanism for final classification. Experiments on Korean (KoACD) and English (Therapist QA) datasets demonstrate that incorporating ELB and LLM-inferred salience scores improves classification performance, especially for distortions with high interpretive ambiguity. Our results suggest a psychologically grounded and generalizable approach for fine-grained reasoning in mental health NLP. The dataset and implementation details are publicly accessible.
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。