推理是视频泛化所需的一切：一个带有子问题评估的反事实基准
Reasoning is All You Need for Video Generalization: A Counterfactual Benchmark with Sub-question Evaluation
AI总结：
本文提出COVER反事实视频推理基准，通过子问题分解评估多模态大语言模型在动态环境中的推理能力，并证明增强推理能力对提升视频理解稳健性至关重要。
摘要：
反事实推理对于稳健的视频理解至关重要，但在现有多模态基准中仍未得到充分探索。本文介绍了COVER（反事实视频推理），这是一个多维度的多模态基准，系统性地在抽象-具体和感知-认知维度上评估多模态大语言模型（MLLMs）。与以往的多模态基准不同，COVER将复杂查询分解为结构化的子问题，从而实现细粒度的推理分析。在商用和开源模型上的实验表明，子问题准确率与反事实推理性能之间存在强相关性，凸显了结构化推理在视频理解中的作用。此外，我们的结果揭示了一个关键见解：增强模型的推理能力对于提高视频理解的稳健性至关重要。COVER为评估多模态大语言模型在动态环境中的逻辑推理能力建立了一个新标准。我们的工作可在https://github.com/gongyifan-hash/COVER-Benchmark获取。
英文摘要：
Counterfactual reasoning is crucial for robust video understanding but remains underexplored in existing multimodal benchmarks. In this paper, we introduce \textbf{COVER} (\textbf{\underline{CO}}unterfactual \textbf{\underline{V}}id\textbf{\underline{E}}o \textbf{\underline{R}}easoning), a multidimensional multimodal benchmark that systematically evaluates MLLMs across the abstract-concrete and perception-cognition dimensions. Beyond prior multimodal benchmarks, COVER decomposes complex queries into structured sub-questions, enabling fine-grained reasoning analysis. Experiments on commercial and open-source models reveal a strong correlation between sub-question accuracy and counterfactual reasoning performance, highlighting the role of structured inference in video understanding. Furthermore, our results suggest a key insight: enhancing the reasoning capability of models is essential for improving the robustness of video understanding. COVER establishes a new standard for assessing MLLMs' logical reasoning abilities in dynamic environments. Our work is available at https://github.com/gongyifan-hash/COVER-Benchmark.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
