@inproceedings{wen-etal-2025-listen,
    title = "Listen, Watch, and Learn to Feel: Retrieval-Augmented Emotion Reasoning for Compound Emotion Generation",
    author = "Wen, Zhuofan  and
      Lian, Zheng  and
      Chen, Shun  and
      Yao, Hailiang  and
      Yang, Longjiang  and
      Liu, Bin  and
      Tao, Jianhua",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/display_plenaries/2025.findings-acl.590/",
    pages = "11313--11327",
    ISBN = "979-8-89176-256-5",
    abstract = "The ability to comprehend human emotion using multimodal large language models (MLLMs) is essential for advancing human-AI interaction and multimodal sentiment analysis. While psychology theory-based human annotations have contributed to multimodal emotion tasks, the subjective nature of emotional perception often leads to inconsistent annotations, limiting the robustness of current models. Addressing these challenges requires more fine-grained methods and evaluation frameworks. In this paper, we propose the Retrieval-Augmented Emotion Reasoning (RAER) framework, a plug-and-play module that enhances MLLMs' ability to tackle compound and context-rich emotion tasks. To systematically evaluate model performance, we introduce the Stimulus-Armed Bandit (SAB) framework, designed to benchmark emotional reasoning capabilities. Additionally, we construct the Compound Emotion QA dataset, an AI-generated multimodal dataset aimed at strengthening emotion understanding in MLLMs. Experimental results demonstrate the effectiveness of RAER across both traditional benchmarks and SAB evaluations, highlighting its potential to enhance emotional intelligence in multimodal AI systems."
}