@inproceedings{he-etal-2026-uncertainty,
    title = "Uncertainty-Calibrated Elastic Alignment for Multimodal Sentiment Analysis with Missing Modalities",
    author = "He, Kang  and
      Ding, Yuzhe  and
      Fu, Rao  and
      Feng, Yukang  and
      Zhang, Kaipeng  and
      Liu, Yiming  and
      Li, Fei  and
      Teng, Chong  and
      Ji, Donghong",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.260/",
    pages = "5268--5288",
    ISBN = "979-8-89176-395-1",
    abstract = "Multimodal sentiment analysis (MSA) in real-world scenarios is often challenged by dynamically missing modalities. Existing methods predominantly rely on deterministic imputation and rigid alignment, which compels the model to overfit noise in ambiguous regions while neglecting the decision shift induced by modality inertia. To address these issues, we propose a novel uncertainty-calibrated elastic alignment framework, termed EASE. Specifically, we employ probabilistic imputation to capture cross-modal ambiguity and leverage the estimated uncertainty to drive elastic alignment, thereby adaptively relaxing constraints in ambiguous regions to avoid rigid fitting. Meanwhile, we introduce cross-view predictive consistency constraints to unify discriminative logic across different modality views, stabilizing the decision boundary under modality degradation. Extensive experiments demonstrate that EASE consistently outperforms existing state-of-the-art baselines across multiple benchmarks, exhibiting exceptional robustness particularly under high missing-rate scenarios."
}