@inproceedings{jin-etal-2026-pedagogybench,
    title = "{P}edagogy{B}ench: A Cognitive-Driven Benchmark for Multimodal Instructional Video Understanding",
    author = "Jin, Xiaokang  and
      Zhu, Jia  and
      Liu, Jingjiang  and
      Shi, Yabing  and
      Guan, Jueqi  and
      Chen, Hao  and
      De Meo, Pasquale",
    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.614/",
    pages = "12621--12647",
    ISBN = "979-8-89176-395-1",
    abstract = "Existing video understanding benchmarks mainly emphasize general visual recognition and reasoning, but do not adequately capture the pedagogical logic embedded in instructional videos. To address this gap, we present PedagogyBench, a multimodal benchmark for instructional video understanding grounded in pedagogical cognition. We introduce a pedagogy-driven segmentation strategy and a dual-stream semantic injection pipeline that combines machine pre-annotation with expert refinement, enabling the construction of a dataset organized around a cognitive pyramid with four levels and 20 fine-grained tasks. We further propose the Cognitive Fidelity Score (CFS) to measure the balance of model performance across pedagogical cognitive dimensions. Experiments on 12 multimodal large language models reveal a clear generative gap, where models perform relatively well on discriminative tasks but degrade on higher-order pedagogical diagnosis, often relying on parametric memory rather than grounded visual perception. Project resources are available at https://github.com/Shallcom/PedagogyBench."
}