AI 中文总结
针对多模态错误信息检测，提出验证笔记本学习框架VNL，通过构建包含决策原则等的笔记本，在推理时指导验证新示例，实验显示其性能优于基线，能提高源归因且紧凑可解释，无需模型训练积累知识。
AI 中文摘要
多模态错误信息验证具有挑战性，因为误导性信号可能来自帖子的不同部分，需要不同形式的证据。语言与视觉模型（LVLMs）适用于此任务，但其验证性能常取决于应用于每个实例的推理过程。现有方法通过更强的提示、检索或审议来改进此过程，但很少保留从先前示例中学到的验证模式。我们提出验证笔记本学习（VNL），这是一个非参数框架，在推理前为冻结的LVLM学习外部验证过程。VNL构建一个包含决策原则、证据线索和常见陷阱的紧凑笔记本。该笔记本在推理期间保持不变，并指导新示例的验证。实验表明，VNL始终优于一系列竞争基线。进一步分析表明，验证笔记本在保持紧凑和可解释的同时，提高了细粒度源归因，提供了一种无需模型训练即可积累验证知识的有效方法。
英文摘要
Multimodal misinformation verification is challenging because misleading signals may come from different parts of a post and require different forms of evidence. LVLMs are well suited to this task, but their verification performance often depends on the inference procedure applied to each instance. Existing methods improve this procedure through stronger prompting, retrieval, or deliberation, but rarely retain the verification patterns learned from previous examples. We propose Verification-Notebook Learning (VNL), a non-parametric framework that learns an external verification procedure for a frozen LVLM before inference. VNL builds a compact notebook of decision principles, evidence cues, and recurring pitfalls from prior verification experience. The notebook remains fixed during inference and guides the verification of new examples. Rather than updating model parameters or storing demonstrations, VNL records learned knowledge in an artifact that can be inspected directly. Experiments show that VNL consistently outperforms a range of competitive baselines. Further analyses show that the Verification Notebook improves fine-grained source attribution while remaining compact and interpretable, providing an effective way to accumulate verification knowledge without model training.
