TL;DR
The results indicate that explicitly modeling semantic conflict as a discriminative feature effectively improves detection precision and generalization, providing a robust solution for factual verification in complex media environments.
TERN induces latent deception types from image-side multimodal features through prototype-based clustering, uses the induced assignments as structural priors for downstream veracity prediction, disentangles type-discriminative factors from semantic content, and performs type-conditioned hierarchical reasoning over text semantics, image authenticity, and cross-modal consistency.
DAR-Lite is proposed, a serial two-stage framework that rethinks the detection pipeline through explicit decoupling of representation denoising and contextual reasoning, and achieves a favorable balance between detection performance and computational cost.
The rapid dissemination of rumors on social media at their early stages poses significant threats to public safety and social stability. While response-based methods usually depend on user comments and reposts and therefore suffer from inherent latency, existing content-based methods still struggle to extract discriminative evidence from noisy short texts and subtle visual inconsistencies under zero-response conditions. To address this issue, we propose SMD-Net, a multimodal framework for early zero-response rumor detection. In the textual branch, a selective state-space encoder is used to model fragmented and noisy posts. In the visual branch, an enhanced TransXNet backbone is designed to improve the representation of fine-grained suspicious patterns and cross-layer feature interactions. An adaptive gated fusion module is further introduced to integrate textual and visual features for final prediction. Experiments on the Weibo and PHEME datasets show that SMD-Net outperforms the compared content-based baselines, achieving 92.60% accuracy on Weibo and 90.27% accuracy on PHEME under the strict zero-response setting. These results suggest that the proposed framework provides an effective solution for early multimodal rumor detection when propagation-based evidence is unavailable.
Multimodal fake news combining text and images has become increasingly prevalent, fueled by the rapid dissemination on social media. Existing approaches predominantly rely on supervised learning–driven small multimodal language models, yet they are constrained by the knowledge scope and logical reasoning capabilities limited by training data: their performance degrades significantly when encountering novel content not covered in the training data, and they typically provide only uninterpretable binary true/false predictions. To address these challenges, we propose the Metacognitive Agentic Reasoning for Multimodal Fake News Detection(MAR), a framework that integrates multi-agent metacognitive debate with external knowledge retrieval to enhance the accuracy, generalization, and interpretability of multimodal fake news detection. At its core, MAR introduces a news-domain informed and metacognition-inspired multi-agent reasoning mechanism: it first generates several prior pseudo-labels of the news domain, and defines the characteristics of two opposing agents (i.e., Believer and Skeptic) leveraging these pseudo-labels; then, the Believer and Skeptic go through a three-stage ''Draft – Self-Critique – Refine'' interactive debate simulating humans' learning behavior, called the metacognitive debate. Specifically, MAR first generates an initial evidence-grounded judgment (Draft), then critically reflects on their own and others' arguments (Self-Critique), and finally iteratively refines their conclusions by incorporating internal or external evidence (Refine). To improve factual reliability, the framework dynamically retrieves trustworthy external knowledge via web and reverse image searches, thereby mitigating the hallucinations inherent in large language models. Experiments show that MAR achieves state-of-the-art performance on two benchmarks and significantly outperforms existing methods in terms of generalization and interpretability. The source code is available at https://github.com/Averdgr/MAR_KDD.
With the rapid growth of social media, online news has become increasingly multimodal, combining textual and visual information, posing new challenges for fake news detection. Existing methods often suffer from redundant features, distribution differences across modalities, and insufficient modeling of semantic interactions. To address these issues, this paper proposes an Adaptive Binary Osprey Optimization Algorithm and Cross-modal Disentangled Fusion model (ABOOA-CDF). First, an Adaptive Binary Osprey Optimization Algorithm (ABOOA) is developed for multimodal feature selection by integrating chaotic initialization, adaptive search, and binary mapping strategies to identify informative feature subsets. Then, a Cross-modal Relation Disentanglement Module (CRDM) is introduced to decompose multimodal representations into shared, discrepant, and complementary components, thereby enhancing semantic relationship modeling. Furthermore, an Adaptive Semantic Fusion Module (ASFM) dynamically learns fusion weights to generate discriminative multimodal representations. Experimental results demonstrate that ABOOA-CDF effectively improves detection performance. Compared with MFO and OOA, the proposed method achieves Accuracy improvements of 1.02 and 2.66 percentage points, respectively, verifying its effectiveness in feature optimization, cross-modal relation modeling, and semantic fusion.