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.
Abstract
Multimodal fake news detection remains challenging because deceptive posts exhibit heterogeneous manipulation patterns, while most existing methods still rely on a unified fusion strategy. This mismatch limits their ability to adapt to different evidence preferences across samples, encourages entanglement between deception cues and topical semantics, and weakens decision making when textual, visual, and cross-modal signals conflict. To address these issues, we propose TERN, a type-aware evidence reasoning network for multimodal fake news detection. 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. Experiments on MR2-Chinese, MR2-English, Weibo, and PHEME show that TERN achieves an average accuracy of 93.21% and an average F1 score of 91.09% while also improving Matthews correlation coefficient over representative multimodal baselines.
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.
Zi-Heng Wang, Junfang Song, Shuyu Wang et al.· Multimedia Systems· 0 citations
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.
Wenyu Chen, Hengbing Dong, Junhao Wa et al.· Proceedings of the 32nd ACM...· 0 citations
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.
Maolin Wang, Ziting Mai, Zichun Liu et al.· Proceedings of the 32nd ACM...· 0 citations
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.
Misinformation spreads rapidly online, making it challenging to separate fact from falsehood. Many existing detection models focus only on text or images, limiting their effectiveness. Text-based models may overlook visual cues, while image-based models may miss subtle linguistic patterns. In this work, we explore whether paraphrased text can improve fake news detection accuracy by helping the model focus on meaning rather than wording. We propose, a multi-modal fake news detection framework that combines DistilBERT for text encoding, FLAN-T5 for generating paraphrased variants, and visual features extracted using either ResNet-34 or CLIP ViT. By evaluating our method across both visual backbones, we analyze the impact of paraphrasing on different model architectures. Experiments on the Fakeddit dataset show that paraphrasing increases overall accuracy by 2–4%, reaching up to 79–82%, and improves F1-score to around 78–80%. Results confirm that text augmentation through paraphrasing consistently improves detection performance across both types of visual models, making the system more robust against reworded misinformation. Overall, the proposed architecture demonstrates an efficient and scalable approach to detecting fake news by combining semantic understanding, visual context, and paraphrased text.
Sonali Ajankar, Mrunalraj Redij, Nikhil B. Khandare et al.· 2026 7th International Confe...· 0 citations
HEF-XFND is proposed, a hybrid explainable feature-fusion framework that combines sparse lexical evidence, contextual transformer representations, source-level credibility indicators, and calibrated ensemble learning that addresses three recurring limitations in fake-news research.
Raju M, Subalakshmi Kannan, P. P· International journal of res...· 0 citations