arXiv cs.CL· Kai Qian, Dongjie Xu, Weijie Shi, Jiaqi Wang, Haolun Ma, Jia Zhu, Jiajie Xu·· 13 小时前AI 评分20
MLCCD：跨 MLLM 层解耦一致性与冲突，用于多模态假新闻检测
Decoupling Consistency and Conflict across MLLM Layers for Fake News Detection
AI 导读
研究者提出 Multi-Level Consistency and Conflict Decoupling（MLCCD），从多模态大模型不同层捕捉不同层级的冲突，用于多模态假新闻检测。
正文 · 原文
Abstract:The trustworthiness of Web content faces a growing threat from multimodal fake news. Real news usually shows aligned image-text semantics, while fake news often contains a few conflicts at varying levels, such as mismatches in objects, scenes, events, and claims. However, existing methods usually treat consistency and conflict in a coarse and static way, limiting their ability to capture sparse conflicts and adapt to varying conflict levels. Inspired by the distinct knowledge encoded across layers in large language models, we propose Multi-Level Consistency and Conflict Decoupling (MLCCD), which captures conflicts at different levels from different layers of multimodal large language models (MLLMs). Specifically, we first use the MLLM's final decision representation to select visual and textual tokens relevant to the task, preventing irrelevant content from diluting sparse conflicts. Then, we preserve tokens whose representations change sharply between adjacent layers, capturing the knowledge each layer adds. Finally, we decouple this knowledge into consistency and conflict evidence and aggregate each across layers with its own router, adapting to varying conflict levels. Experiments on three benchmarks show that MLCCD outperforms existing methods.
| Comments: | 12 pages |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.36569 [cs.CV] |
| (or arXiv:2610.36569v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.36569 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Kai Qian [view email]
[v1]
Tue, 27 Oct 2026 03:18:47 UTC (411 KB)
来源：arXiv cs.CL · arxiv.org