大模型情绪推理脆弱，表面识别强但深层认知不稳。
Large language models show fragile cognitive reasoning about human emotions
- 基于认知评价理论构建新评测基准CoRE，考察模型对情绪背后认知维度的理解。
- 模型虽能捕捉认知与情绪的系统关联，但判断与人类存在偏差且易受上下文干扰。
- 适合关注AI情绪理解局限性、认知推理评估的研究者参考。
情感计算旨在通过使机器能够参与人类情感，推动人工智能的全面发展。近期的基础模型，尤其是大语言模型（LLMs），已在情绪相关任务上进行了训练和评估，通常采用带有离散情绪标签的监督学习。此类评估主要聚焦于表层现象，如识别表达或诱发的情绪，未明确这些系统是否以具有认知意义的方式进行情绪推理。本文探讨大模型能否仅通过内在认知维度而非情绪标签来推理情绪。基于认知评价理论，我们提出了CoRE——一个大规模基准，用于探测模型在解读情绪化情境时所依赖的隐含认知结构。我们评估了模型与人类评价模式的一致性、内部一致性、跨模型泛化能力以及对上下文变化的鲁棒性。结果表明，大模型能够捕捉认知评价与情绪之间的系统性关系，但与人类判断存在偏差，并在不同上下文中表现出不稳定性。
原文摘要 · Abstract (English)
Affective computing seeks to support the holistic development of artificial intelligence by enabling machines to engage with human emotion. Recent foundation models, particularly large language models (LLMs), have been trained and evaluated on emotion-related tasks, typically using supervised learning with discrete emotion labels. Such evaluations largely focus on surface phenomena, such as recognizing expressed or evoked emotions, leaving open whether these systems reason about emotion in cognitively meaningful ways. Here we ask whether LLMs can reason about emotions through underlying cognitive dimensions rather than labels alone. Drawing on cognitive appraisal theory, we introduce CoRE, a large-scale benchmark designed to probe the implicit cognitive structures LLMs use when interpreting emotionally charged situations. We assess alignment with human appraisal patterns, internal consistency, cross-model generalization, and robustness to contextual variation. We find that LLMs capture systematic relations between cognitive appraisals and emotions but show misalignment with human judgments and instability across contexts.
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。