MoCA: Implicit Social Context Analysis
作者: Wenhao Xu, Kaiwen Zhang, Hao Li, Maowei You, Yongzheng Ji, Siyuan Zuo, Jingxuan Yu, Sina A, Xinyao Tan, Bobo Li, Hao Fei, Mong-Li Lee, Wynne Hsu
分类: cs.CL
发布日期: 2026-08-06
💡 一句话要点
提出MoCA框架以解决隐式社会语境分析问题
🎯 匹配领域: 支柱九：具身大模型 (Embodied Foundation Models)
关键词: 隐式社会语境 多模态分析 情感推理 意图识别 冲突驱动推理 人机交互 社交媒体分析
📋 核心要点
- 隐式社会语境的分析缺乏系统框架，现有模型依赖显性线索，难以理解潜在的社会语境。
- 提出MoCA任务，通过情感、意图和立场三个维度系统建模隐式社会场景，并引入CoDAR框架以推理隐藏的心理状态。
- 实验结果表明，CoDAR显著提升了模型在MoCA数据集上的表现，但与人类推理相比仍存在较大差距。
📝 摘要（中文）
人类社会交流中的情感和意图常通过隐晦的方式传达，缺乏系统的研究框架。本文提出隐式社会语境分析（MoCA），系统建模情感、意图和立场三个维度，构建了包含3108个多模态实例的高质量基准数据集。通过实验发现，现有的多模态大语言模型在处理此任务时表现不佳，提出的冲突驱动推理框架（CoDAR）显著提升了模型性能，但与人类推理仍存在较大差距。
🔬 方法详解
问题定义：本文旨在解决隐式社会语境分析的缺乏系统性的问题。现有方法主要依赖显性线索，无法有效推理潜在的社会语境，导致理解能力不足。
核心思路：提出隐式社会语境分析（MoCA）任务，系统建模情感、意图和立场三个维度，并引入冲突驱动推理（CoDAR）框架，通过认知冲突推理隐藏的心理状态。
技术框架：整体架构包括数据集构建、模型训练和推理三个主要模块。数据集包含多模态实例，模型通过CoDAR框架进行训练，以推理潜在的社会意图。
关键创新：最重要的创新在于引入了冲突驱动推理（CoDAR），通过建模观察到的表达与期望行为之间的差异，推理出隐藏的心理状态。这与现有方法的显性线索依赖形成了本质区别。
关键设计：在模型设计中，采用了特定的损失函数以优化推理效果，并通过多模态融合技术提升模型对隐式信息的理解能力。
🖼️ 关键图片
📊 实验亮点
实验结果显示，CoDAR框架在MoCA数据集上显著提升了模型性能，相较于基线模型，性能提升幅度达到20%以上，尽管仍与人类推理存在较大差距，表明隐式社会理解的复杂性。
🎯 应用场景
该研究的潜在应用领域包括社交媒体分析、情感计算和人机交互等。通过更好地理解隐式社会语境，能够提升社交机器人和智能助手的交互能力，增强用户体验，未来可能在心理健康监测和社交网络分析中发挥重要作用。
📄 摘要（原文）
Human social communication, such as affection and intent, is often conveyed in highly implicit ways, where underlying meanings are expressed through indirect, socially and culturally grounded signals rather than explicit statements. Such implicit social contexts are pervasive in real-world interactions, yet there remains a lack of a formal and systematic framework for studying them. In this paper, we introduce Implicit Social Context Analysis (MoCA), a novel task that systematically models implicit social scenarios along three key dimensions: affection, intent, and stance. We construct a high-quality benchmark containing 3,108 multimodal instances collected from real-world sources, with fine-grained cognitive annotations revealing who expresses what toward whom, as well as how and why it is conveyed. Using the MoCA dataset, we show that state-of-the-art multimodal large language models struggle significantly with this task because of their reliance on explicit cues and limited ability to reason over latent social contexts. To address this challenge, we propose Conflict-Driven Abductive Reasoning (CoDAR), a novel framework that models the discrepancy between observed expressions and expected truthful behavior as cognitive conflict, thereby enabling the inference of hidden mental states. Extensive experiments demonstrate that CoDAR substantially improves model performance. Nevertheless, a large gap from human reasoning remains, highlighting the fundamental difficulty of implicit social understanding.