检测并修复多模态新闻预告中的关键信息遗漏，防止误导性解读。
What's Left Unsaid? Detecting and Correcting Misleading Omissions in Multimodal News Previews
- 构建模拟预览与上下文理解的多阶段框架，生成首个针对遗漏误导的基准数据集。
- 发现大模型在识别信息遗漏导致的误导上存在明显盲区，8B模型经优化后达到235B模型水平。
- 提出OMGuard系统，结合语义感知微调与理由引导的内容修正，支持图文协同干预。
即使事实正确，社交媒体新闻预览（图文组合）也可能因选择性省略关键背景而引发读者判断偏差，这种隐蔽伤害比虚假信息更难察觉，但研究不足。为此，我们构建了多阶段流水线，模拟预览与上下文理解，建立MM-Misleading基准。基于该基准，系统评估开源多模态大模型，揭示其在遗漏型误导检测上的显著盲区。进一步提出OMGuard，融合（1）解释感知微调以提升误导检测能力，（2）理由引导的误导内容修正，通过显式理由指导标题重写以降低误导印象。实验表明，OMGuard使8B模型的检测准确率接近235B模型水平，并实现更强端到端修正效果。分析显示，误导多源于局部叙事偏移（如缺失背景），而非整体框架变化；且图像驱动场景下仅文本修正无效，凸显视觉干预必要性。
原文摘要 · Abstract (English)
Even when factually correct, social-media news previews (image-headline pairs) can induce interpretation drift: by selectively omitting crucial context, they lead readers to form judgments that diverge from what the full article supports. This covert harm is subtler than explicit misinformation, yet remains underexplored. To address this gap, we develop a multi-stage pipeline that simulates preview-based and context-based understanding, enabling construction of the MM-Misleading benchmark. Using MM-Misleading, we systematically evaluate open-source LVLMs and uncover pronounced blind spots in omission-based misleadingness detection. We further propose OMGuard, which combines (1) Interpretation-Aware Fine-Tuning for misleadingness detection and (2) Rationale-Guided Misleading Content Correction, where explicit rationales guide headline rewriting to reduce misleading impressions. Experiments show that OMGuard lifts an 8B model's detection accuracy to the level of a 235B LVLM while delivering markedly stronger end-to-end correction. Further analysis shows that misleadingness usually arises from local narrative shifts, such as missing background, instead of global frame changes, and identifies image-driven cases where text-only correction fails, underscoring the need for visual interventions.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。