@inproceedings{shi-etal-2026-msvbench,
    title = "{MSVB}ench: Towards Human-Level Evaluation of Multi-Shot Video Generation",
    author = "Shi, Haoyuan  and
      li, Yunxin  and
      Deng, Nanhao  and
      Xu, Zhenran  and
      Chen, Xinyu  and
      Wang, Longyue  and
      Hu, Baotian  and
      Zhang, Min",
    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.1203/",
    pages = "24034--24058",
    ISBN = "979-8-89176-395-1",
    abstract = "The evolution of video generation toward complex, multi-shot narratives has exposed a critical deficit in current evaluation methods. Existing benchmarks remain anchored to single-shot paradigms, lacking the comprehensive story assets and cross-shot metrics required to assess long-form coherence and appeal. To bridge this gap, we introduce $\textbf{MSVBench}$, the first comprehensive benchmark featuring hierarchical scripts and reference images tailored for $\textbf{M}$ulti-$\textbf{S}$hot $\textbf{V}$ideo generation. We propose a hybrid evaluation framework that synergizes the high-level semantic reasoning of Large Multimodal Models (LMMs) with the fine-grained perceptual rigor of domain-specific expert models. Evaluating 20 video generation methods across diverse paradigms, we find that current models{---}despite strong visual fidelity{---}primarily behave as visual interpolators rather than true world models. We further validate the reliability of our benchmark by demonstrating a state-of-the-art Spearman{'}s rank correlation of $\textbf{0.944}$ with human judgments. Finally, MSVBench extends beyond evaluation by providing a scalable supervisory signal. Fine-tuning a lightweight model on its pipeline-refined reasoning traces yields human-aligned performance comparable to commercial models like Gemini-2.5-Flash."
}