揭穿欺骗性视觉：在多模态大语言模型上基准测试误导性图表问答
Unmasking Deceptive Visuals: Benchmarking Multimodal Large Language Models on Misleading Chart Question Answering
AI总结：
本文提出Misleading ChartQA基准，包含3,026个涵盖21种误导类型和10种图表类型的示例，系统评估24个多模态大语言模型检测误导性图表的能力，并提出区域感知推理流程以提升模型准确性。
摘要：
误导性可视化通过操纵图表表示来支持特定主张，可能扭曲感知并导致错误结论。尽管已有数十年的研究，它们仍然是一个普遍存在的问题，对公众理解构成风险，并为涉及数据驱动通信的AI系统带来安全隐患。虽然近期多模态大语言模型（MLLMs）展现出强大的图表理解能力，但其检测和解释误导性图表的能力仍未得到探索。我们引入了Misleading ChartQA基准，这是一个大规模多模态数据集，旨在评估MLLMs在误导性图表推理上的表现。该数据集包含3,026个经过整理的示例，涵盖21种误导类型和10种图表类型，每个示例均配有标准化图表代码、CSV数据、多项选择题和标注解释，并通过迭代式MLLM检查和专家人工审查进行验证。我们对24个最先进的MLLMs进行了基准测试，分析了它们在各类误导类型和图表格式上的表现，并提出了一种新颖的区域感知推理流程，以提高模型准确性。我们的工作为开发稳健、可信且符合负责任视觉传播要求的MLLMs奠定了基础。
英文摘要：
Misleading visualizations, which manipulate chart representations to support specific claims, can distort perception and lead to incorrect conclusions. Despite decades of research, they remain a widespread issue, posing risks to public understanding and raising safety concerns for AI systems involved in data-driven communication. While recent multimodal large language models (MLLMs) show strong chart comprehension abilities, their capacity to detect and interpret misleading charts remains unexplored. We introduce Misleading ChartQA benchmark, a large-scale multimodal dataset designed to evaluate MLLMs on misleading chart reasoning. It contains 3,026 curated examples spanning 21 misleader types and 10 chart types, each with standardized chart code, CSV data, multiple-choice questions, and labeled explanations, validated through iterative MLLM checks and expert human review. We benchmark 24 state-of-the-art MLLMs, analyze their performance across misleader types and chart formats, and propose a novel region-aware reasoning pipeline that enhances model accuracy. Our work lays the foundation for developing MLLMs that are robust, trustworthy, and aligned with the demands of responsible visual communication.
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。
