发表机构
Artificial Intelligence Research Institute; Shenzhen University of Advanced Technology（人工智能研究院; 深圳理工大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
SAFE-MR框架将声明真实性与证据充分性分离，通过关系感知图与证据干预实现选择性多模态谣言检测，在三个基准上显著提升宏F1并降低选择性预测错误。
AI 中文摘要
多模态谣言检测器日益依赖检索到的证据，然而相关证据未必足以支持验证。缺失来源、重复报道和未解决的矛盾可能在缺乏充分支持的情况下产生自信的预测。我们提出SAFE-MR，一个将声明真实性判断与证据充分性评估相分离的框架。该方法将图像-文本帖子分解为可验证的声明，构建关系感知的声明-证据图，并利用来源和上下文兼容性聚合证据。独立的真实性和充分性预测头支持选择性预测，而证据干预则鼓励模型在无关添加下保持稳定性，并对证据移除保持敏感性。在NewsCLIPpings、VERITE和XFacta数据集上，SAFE-MR分别取得了91.2%、75.8%和85.2%的宏F1分数。与配备证据的匹配骨干网络相比，其宏F1分数分别提高了2.2、4.9和4.8个百分点。在诊断性选择集上，SAFE-MR将AURC从最大概率拒绝的0.105降至0.075，并将80%覆盖率下的错误率从13.8%降至8.5%。证据扰动和消融实验结果支持了充分性学习和干预训练在改进选择性验证中的作用。
英文摘要
Multimodal rumor detectors increasingly rely on retrieved evidence, yet relevant evidence is not necessarily sufficient for verification. Missing provenance, duplicated reports, and unresolved contradictions can produce confident predictions without adequate support. We introduce SAFE-MR, a framework that separates claim veracity from evidence sufficiency. The method decomposes image-text posts into verifiable claims, constructs a relation-aware claim-evidence graph, and aggregates evidence using provenance and contextual compatibility. Separate veracity and sufficiency heads support selective prediction, while evidence interventions encourage stability under irrelevant additions and sensitivity to evidence removal. On NewsCLIPpings, VERITE, and XFacta, SAFE-MR achieves macro-F1 scores of 91.2%, 75.8%, and 85.2%, respectively. Against the matched backbone with evidence, its macro-F1 gains are 2.2, 4.9, and 4.8 percentage points. On the diagnostic selection set, SAFE-MR reduces AURC from 0.105 for maximum-probability rejection to 0.075 and lowers error at 80% coverage from 13.8% to 8.5%. Evidence-perturbation and ablation results support the role of sufficiency learning and intervention training in improving selective verification.
