Misleading visualizations are a potent driver of misinformation on social media and the web. By violating chart design principles, they distort data and lead readers to draw inaccurate conclusions. Prior work has shown that both humans and multimodal large language models (MLLMs) are frequently deceived by such visualizations. Automatically detecting misleading visualizations and identifying the specific design rules they violate could help protect readers and reduce the spread of misinformation. However, the training and evaluation of AI models has been limited by the absence of large, diverse, and openly available datasets. In this work, we introduce Misviz, a benchmark of 2,604 real-world visualizations annotated with 12 types of misleaders. To support model training, we also create Misviz-synth, a synthetic dataset of 57,665 visualizations generated using Matplotlib and based on real-world data tables. We perform a comprehensive evaluation on both datasets using state-of-the-art MLLMs, rule-based systems, and image-axis classifiers. Our results reveal that the task remains highly challenging. We release Misviz, Misviz-synth, and the accompanying code.

翻译：误导性可视化图表是社交媒体和网络上虚假信息的重要推手。通过违反图表设计原则，它们扭曲数据，导致读者得出不准确的结论。先前的研究表明，人类和多模态大语言模型（MLLMs）都经常被此类可视化图表所欺骗。自动检测误导性可视化图表并识别其违反的具体设计规则，有助于保护读者并减少虚假信息的传播。然而，由于缺乏大规模、多样化和公开可用的数据集，AI模型的训练和评估一直受到限制。在这项工作中，我们引入了Misviz，这是一个包含2,604个真实世界可视化图表的基准数据集，并标注了12种误导类型。为了支持模型训练，我们还创建了Misviz-synth，这是一个基于真实数据表、使用Matplotlib生成的包含57,665个可视化图表的合成数据集。我们使用最先进的MLLMs、基于规则的系统以及图像轴分类器，在这两个数据集上进行了全面评估。我们的结果表明，这项任务仍然极具挑战性。我们将发布Misviz、Misviz-synth及附带代码。