T-IMPACT：面向上下文图像-文本操纵的严重性感知基准
T-IMPACT: A Severity-Aware Benchmark for Contextual Image-Text Manipulation
AI总结：
提出T-IMPACT基准，包含98,786个图像-文本对，涵盖原始、仅图像、仅文本和联合操纵，通过校准的连续严重性分数和粗粒度标签评估操纵对上下文理解的影响，实验表明现有模型在严重性预测上仍远弱于人类判断。
摘要：
近期视觉-语言模型和生成编辑系统的进展使得通过修改图像、文本或两者联合来产生有说服力的多模态虚假信息变得越来越容易。然而，现有数据集主要关注真实性、上下文不匹配或操纵类型，很少捕捉编辑在多大程度上改变了帖子的可能解读。我们引入了T-IMPACT，一个首次发布的用于操纵新闻风格图像-文本对的严重性感知基准。T-IMPACT包含98,786个样本，涵盖原始、仅图像、仅文本和联合操纵，具有校准的连续严重性信号、粗粒度的低/中/高标签以及支持性的基础元数据。从新闻图像-文本对开始，该流程提取语义锚点，在空间上对其进行基础定位，执行局部图像编辑和受约束的标题重写，并使用有限的人工评分校准上下文影响分数。在此版本中，校准的连续分数是主要的严重性目标，而低/中/高区间应解释为粗粒度的操作桶，而非平衡类别。实验表明，当前模型可以恢复一些真实性信号，但严重性预测仍然困难得多，且仅与人类判断弱对齐。T-IMPACT为研究超越二元真实/虚假分类的多模态操纵向分级上下文影响提供了初步基准。
英文摘要：
Recent advances in vision-language models and generative editing systems have made it increasingly easy to produce persuasive multimodal misinformation by altering images, text, or both jointly. However, existing datasets focus mainly on authenticity, out-of-context mismatch, or manipulation type, and rarely capture how strongly an edit changes the likely interpretation of a post. We introduce T-IMPACT, a first-release severity-aware benchmark for manipulated news-style image-text pairs. T-IMPACT contains 98,786 examples spanning pristine, image-only, text-only, and joint manipulations, with a calibrated continuous severity signal, coarse low/medium/high labels, and supporting grounding metadata. Starting from a news image-text pair, the pipeline extracts semantic anchors, grounds them spatially, performs localized image edits and constrained caption rewrites, and calibrates contextual-impact scores using limited human ratings. In this release, the calibrated continuous score is the primary severity target, while the low/medium/high bands should be interpreted as coarse operating buckets rather than balanced classes. Experiments show that current models recover some authenticity signal, but severity prediction remains substantially harder and only weakly aligned with human judgment. T-IMPACT provides an initial benchmark for studying multimodal manipulation beyond binary real/fake classification toward graded contextual impact.
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。
