用排序学习提升情感细微差别识别，让AI更懂情绪深意
Rank-O-ToM: Unlocking Emotional Nuance Ranking to Enhance Affective Theory-of-Mind
- 通过序数排序对齐置信度与情感光谱，改善模型校准
- 引入合成样本增强对复杂情绪的感知能力，提升情感理解精度
- 适合研究情感计算、人机共情交互的学者和工程师
面部表情识别（FER）是人工智能理解情感细微差别的基础，对实现情感化心智理论（ToM）至关重要。然而现有模型普遍存在校准不足、难以捕捉情绪强度与复杂性的问题。为此，我们提出情感细微差别排序框架（Rank-O-ToM），利用序数排序机制将模型置信度与情感连续谱对齐。通过引入反映多样情感复杂性的合成样本，该框架增强了对情绪细微差别的理解能力，显著提升了AI在情感状态推理方面的表现。
原文摘要 · Abstract (English)
Facial Expression Recognition (FER) plays a foundational role in enabling AI systems to interpret emotional nuances, a critical aspect of affective Theory of Mind (ToM). However, existing models often struggle with poor calibration and a limited capacity to capture emotional intensity and complexity. To address this, we propose Ranking the Emotional Nuance for Theory of Mind (Rank-O-ToM), a framework that leverages ordinal ranking to align confidence levels with the emotional spectrum. By incorporating synthetic samples reflecting diverse affective complexities, Rank-O-ToM enhances the nuanced understanding of emotions, advancing AI's ability to reason about affective states.
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。