Zhi Zeng, Jiaying Wu, Minnan Luo, Di Zhang, Yifei Yang, Xiangzheng Kong, Herun Wan, Zihan Ma. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

The rise of micro-videos has reshaped how misinformation spreads, amplifying its speed, reach, and impact on public trust. Existing benchmarks typically focus on a single deception type, overlooking the diversity of real-world cases that involve multimodal manipulation, AI-generated content, cognitive bias, and out-of-context reuse. Meanwhile, most detection models lack fine-grained attribution, limiting interpretability and practical utility. To address these gaps, we introduce WildFakeBench, a large-scale benchmark of over 10,000 real-world micro-videos covering diverse misinformation types and sources, each annotated with expert-defined attribution labels. Building on this foundation, we develop FakeAgent, a Delphi-inspired multi-agent reasoning framework that integrates multimodal understanding with external evidence for attribution-grounded analysis. FakeAgent jointly analyzes content and retrieved evidence to identify manipulation, recognize cognitive and AI-generated patterns, and detect out-of-context misinformation. Extensive experiments show that FakeAgent consistently outperforms existing MLLMs across all misinformation types, while WildFakeBench provides a realistic and challenging testbed for advancing explainable micro-video misinformation detection. Data and code are available at: https://github.com/Aiyistan/FakeAgent.

Social platforms, while facilitating access to information, have also become saturated with a plethora of fake news, resulting in negative consequences. Automatic multimodal fake news detection is a worthwhile pursuit. Existing multimodal fake news datasets only provide binary labels of real or fake. However, real news is alike, while each fake news is fake in its own way. These datasets fail to reflect the mixed nature of various types of multimodal fake news. To bridge the gap, we construct an attributing multi-granularity multimodal fake news detection dataset AMG, revealing the inherent fake pattern. Furthermore, we propose a multi-granularity clue alignment model MGCA to achieve multimodal fake news detection and attribution. Experimental results demonstrate that AMG is a challenging dataset, and its attribution setting opens up new avenues for future research.

Zhi Zeng, Jiaying Wu, Minnan Luo, Herun Wan, Xiangzheng Kong, Zihan Ma, Guang Dai, Qinghua Zheng. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Short videos have become a pivotal medium for news dissemination but have also accelerated the spread of fake news. Although existing detection methods have achieved significant results, they often neglect the impact of noise in multimodal data, resulting in degraded detection accuracy and limited generalization. To address these challenges, we propose the Progressive Noise-Resilient Network (PNRN), a framework designed to adaptively mitigate noise in complex scenarios. PNRN comprises two key components: a unimodal noise-resilient module and a multimodal adaptive fusion module. The unimodal noise-resistant module leverages information bottlenecks to effectively filter modality-specific noise and strengthen feature relevance within individual modalities. The multimodal adaptive fusion module employs dynamic multi-routing and a mixture of experts to dynamically prioritize informative multimodal representations while reducing cross-modal inconsistencies. Experimental results demonstrate that PNRN significantly enhances fake news video detection performance and exhibits strong generalization capabilities in diverse and noisy social environments. Main code is available at https://anonymous.4open.science/r/PNRN-F308.

As short videos become a dominant medium for news dissemination, fake news videos pose increasing threats to public trust and information integrity. Existing methods primarily focus on learning multimodal representations to predict binary veracity labels, yet they overlook the use of external evidence, which is important for identifying more sophisticated fake news that subtly exploits psychological cues and cognitive biases. Moreover, these approaches do not provide fine-grained attribution labels, which are essential for interpretable misinformation governance. To address these limitations, we introduce EvidSV, the first comprehensive benchmark supporting evidence- and attribution-aware fake news video detection. Drawing inspiration from the human cognitive process of interpreting news-related content, we propose MUKE, a multi-view knowledge progressive enhancement learning framework. By jointly analyzing both the news content and supporting evidence, MUKE (1) facilitates the understanding of news semantics to (2) progressively refine shared domain knowledge, and (3) adaptively summarizes multi-view knowledge to assess news veracity. Extensive experiments demonstrate that MUKE consistently outperforms existing methods in both fake news detection and attribution, and generalizes effectively to previously unseen domains. Our code is available at https://github.com/zzeng1998/EvidSV.

Misinformation detectors often rely on superficial cues (i.e., shortcuts) that correlate with misinformation in training data but fail to generalize to the diverse and evolving nature of real-world misinformation. This issue is exacerbated by large language models (LLMs), which can easily generate convincing misinformation using simple prompts. We introduce TruthOverTricks, a unified evaluation paradigm for measuring shortcut learning in misinformation detection. TruthOverTricks categorizes shortcut behaviors into intrinsic shortcut induction and extrinsic shortcut injection, and evaluates seven representative detectors across 14 popular benchmarks, along with two new factual misinformation datasets, NQ-Misinfo and Streaming-Misinfo. Empirical results reveal that existing detectors suffer severe performance degradation when exposed to both naturally occurring and adversarially crafted shortcuts. To address this, we propose the Shortcut Mitigation Framework (SMF), an LLM-augmented data augmentation framework that mitigates shortcut reliance through paraphrasing, factual summarization, and sentiment normalization. SMF consistently enhances robustness across 16 benchmarks, forcing models to rely on deeper semantic understanding rather than shortcut cues.

While the proliferation of fake news poses a significant threat to information integrity, existing efforts to counter it, especially within personalized news recommendation systems, have proven inadequate.Traditional methods, which often rely on classifiers to filter out fake content, are limited by their accuracy and their inability to fully capture the diverse interests of users.To address these challenges, we proposed PRISM-Protection-enhanced Recommendation with Interest-aware Sequential Modeling-a novel framework based on diffusion models.PRISM harnesses the generative and control capabilities of diffusion models to progressively learn the implicit distribution of user interests from their reading history, thereby generating personalized recommendations that align with both their linguistic preferences and interest domains.Furthermore, PRISM incorporates pre-trained authenticity representations as constraints during content generation, ensuring the credibility of the recommended news and effectively curbing the spread of fake news.Comprehensive evaluations from multiple dimensions demonstrate the superiority of our model.

Fake news data, often sampled from the same communities, results in the veracity of news being highly correlated with certain textual and visual entities. This correlation leads fake news classification models to be prone to shortcut learning, quickly overfitting by capturing only shallow spurious correlations between labels and features. Consequently, neural networks trained on such data suffer from poor generalization and potential misclassification under distribution shifts. To address these critical challenges and enhance the robustness of fake news detection, in this paper, we propose a DIsentanglement-based Causality-awarE fake news detection method (DICE). DICE introduces a novel paradigm that moves beyond merely mitigating known correlations or relying on predefined bias categories. Specifically, DICE dynamically constructs multimodal news into a graph neural network, employing learnable node and edge mask disentanglers to effectively model and separate genuine causal relationships from spurious correlations between multimodal features and veracity labels. To reinforce this disentanglement process, we design a novel optimization framework that minimizes extrapolation risk and enforces representation orthogonality, leading to robust disentangled causal and biased representations. Extensive experiments demonstrate that DICE achieves superior performance on five large-scale fake news detection benchmarks. Additionally, our evaluation on a heavily biased fake news dataset demonstrates DICE’s strong generalization, suggesting its potential to inform a new paradigm in causal fake news detection. The code repo is available: https://github.com/mazihan880/DICE Code/.

Chinese idioms pose a significant challenge for machine reading comprehension due to their metaphorical meanings often diverging from their literal counterparts, leading to metaphorical inconsistency. Furthermore, the same idiom can have different meanings in different contexts, resulting in contextual inconsistency. Although deep learning-based methods have achieved some success in idioms reading comprehension, existing approaches still struggle to accurately capture idiom representations due to metaphorical inconsistency and contextual inconsistency of idioms. To address these challenges, we propose a novel model, Multi-Semantic Contrastive Learning Method (MSCLM), which simultaneously addresses metaphorical inconsistency and contextual inconsistency of idioms. To mitigate metaphorical inconsistency, we propose a metaphor contrastive learning module based on the prompt method, bridging the semantic gap between literal and metaphorical meanings of idioms. To mitigate contextual inconsistency, we propose a multi-semantic cross-attention module to explore semantic features between different metaphors of the same idiom in various contexts. Our model has been compared with multiple current latest models (including GPT-3.5) on multiple Chinese idiom reading comprehension datasets, and the experimental results demonstrate that MSCLM outperforms state-of-the-art models.

The swift detection of multimedia fake news has emerged as a crucial task in combating malicious propaganda and safeguarding the security of the online environment.While existing methods have achieved commendable results in modeling entity-level inconsistency, addressing event-level inconsistency following the inherent subject-predicate logic of news and robustly learning news representations from poorquality news samples remain two challenges.In this paper, we propose an Event-dRiven fAke news Detection frAmewoRk (Event-Radar) based on multi-view learning, which integrates visual manipulation, textual emotion and multimodal inconsistency at event-level for fake news detection.Specifically, leveraging the capability of graph structures to capture interactions between events and parameters, Event-Radar captures event-level multimodal inconsistency by constructing an event graph that includes multimodal entity subject-predicate logic.Additionally, to mitigate the interference of poor-quality news, Event-Radar introduces a multi-view fusion mechanism, learning comprehensive and robust representations by computing the credibility of each view as a clue, thereby detecting fake news.Extensive experiments demonstrate that Event-Radar achieves outstanding performance on three large-scale fake news detection benchmarks.Our studies also confirm that Event-Radar exhibits strong robustness, providing a paradigm for detecting fake news from noisy news samples.

Detecting fake news on social media has become a crucial task in combating online misinformation and countering malicious propaganda. Existing methods rely on semantic consistency across modalities to fuse features and determine news authenticity. However, cunning fake news publisher manipulate image to ensure a high level of semantic consistency between news post and image, making it more difficult to distinguish fake news. To this end, we propose MHFFD (Mixed High-Frequency Feature Detector), a novel fake news detection framework that utilizes token-level semantic consistency evaluation to identify key elements in news content and provide guidance for discovering image manipulation and learning better news representations. Extensive experiments demonstrate that MHFFD outperforms state-of-the-art methods on two widely used fake news detection datasets. Further research also validates the effectiveness of token-level semantic alignment and manipulation detection.

The security of Deep Neural Networks (DNNs) has proven to be critical for their applicabilities in real-world scenarios. However, DNNs are well-known to be vulnerable against adversarial attacks, such as adding artificially designed imperceptible magnitude perturbation to the benign input. Therefore, adversarial robustness is essential for DNNs to defend against malicious attacks. Stochastic Neural Networks (SNNs) have recently shown effective performance on enhancing adversarial robustness by injecting uncertainty into models. Nevertheless, existing SNNs are still limited for adversarial defense, as their insufficient representation capability from the fixed uncertainty. In this paper, to elevate feature representation capability of SNNs, we propose a novel yet practical stochastic neural network that maximizes feature distribution variance (MFDV-SNN). In addition, we provide theoretical insights to support the adversarial resistance of MFDV, which primarily derived from the stochastic noise we injected into DNNs. Our research demonstrates that by gradually increasing the level of stochastic noise in a DNN, the model naturally becomes more resistant to input perturbations. Since adversarial training is not required, MFDV-SNN does not compromise clean data accuracy and saves up to 7.5 times computation time. Extensive experiments on various attacks demonstrate that MFDV-SNN improves adversarial robustness significantly compared to other methods.

Short videos turn into an important channel for public sharing, as well as they've become a fertile ground for fake news. Fake news video detection is to judge the veracity of news based on its different modal information, such as video, audio, text, image and social context information. Current detection models tend to learn the multimodal dataset biases within spurious correlations between news modalities and veracity labels as shortcuts, rather than learning how to integrate the multimodal information behind them to reason, resulting in seriously degrading their detection and generalization capabilities. To address this issues, we propose a Multimodal Multi-View Debiasing (MMVD) framework, which makes the first attempt to mitigate various multimodal biases for fake news video detection. Inspired by people's misleading situations by multimodal short videos, we summarize three cognitive biases: static, dynamic and social biases. MMVD put forward a multi-view causal reasoning strategy to learn unbiased dependencies within the cognitive biases, thus enhancing the unbiased prediction of multimodal videos. The extensive experimental results show that the MMVD could improve the detection performance of multimodal fake news video. Studies also confirm that our MMVD can mitigate multiple biases on complex real-world scenarios and improve generalization ability of fake news video detection.

Fake news is usually disseminated in a multimodal form, which incorporates natural language, visual language, and so on. Therefore, many deep learning approaches are proposed to detect multimodal fake news. However, a drawback of existing methods is that they simply fuse unimodal features and ignore the latent semantic alignment of image and text modalities. In this paper, we propose a novel Multimodal Stacked Cross Attention Network (MSCA) to better align and fuse multimodal token-level textual and visual features for fake news detection. Experiments conducted on two publicly available datasets show that our method can significantly improve performance compared with other models. Furthermore, experimental analysis shows that MSCA can effectively align and fuse token-level features of multiple modalities.

The existing models have been achieved great success in capturing and fusing miltimodal semantics of news. However, they paid more attention to the global information, ignoring the interactions of global and local semantics and the inconsistency between different modalities. Therefore, we propose an explainable multi-view semantic fusion model (EMSFM), where we aggregate the important inconsistent semantics from local and global views to compensate the global information. Inspired by various forms of artificial fake news and real news, we summarize four views of multimodal correlation: consistency and inconsistency in the local and global views. Integrating these four views, our EMSFM can interpretatively establish global and local fusion between consistent and inconsistent semantics in multimodal relations for fake news detection. The extensive experimental results show that the EMSFM can improve the performance of multimodal fake news detection and provide a novel paradigm for explainable multi-view semantic fusion.

Multimodal fake news detection has become a topical research of fake news detection. Existing models have made great efforts in capturing and fusing multimodal semantics of news for classification. However, they overlooked mitigating inconsistency between different modalities, which may result in learning biased statistical information. Therefore, we propose a mitigating multimodal inconsistency contrastive learning framework (MMICF), which mitigates inconsistency in multi-modal relations for fake news detection. Inspired by various forms of artificial fake news, we summarize two patterns of multimodal inconsistency: local and global inconsistency. To mitigate local inconsistency in multimodal relations, we use a causal-relation reasoning module by causally removing the direct effects of the textual and visual entities. Considering the influence of global inconsistency in multimodal semantics, our contrastive learning framework mitigates the semantic deviation of contrastive text-image objectives, which are constrained into a unified semantic space by a modal unified module. Thus, our MMICF can jointly mitigate local and global inconsistency for further maximally exploiting multimodal consistent semantics for fake news detection. The extensive experimental results show that the MMICF can improve the performance of multimodal fake news detection and provide a novel paradigm for mitigating multimodal inconsistency contrastive learning.

As news has become an important way to obtain in-formation, the spread of fake news has caused serious social problems, such as misleading readers and damaging the authority of the government. Therefore, fake news detection has become an important field in social network research. One challenge of fake news detection is how to explore the common latent semantics, which are universally implied in fake news. However, the existing methods are not enough for mining this kind of semantic information. Therefore, we proposed a fake news detection framework named Common Latent Semantics Matching Model (CLSMM), which improves the performance of fake news detection by utilizing common latent semantics in fake news. First, we use BERT model to extract common latent semantics of fake news and use summary generation model to extract distinct latent semantics among each piece of news. Second, we rank the semantic credibility score according to the matching degree of the two kinds of latent semantics mentioned above. Finally, these semantic credibility scores are injected into a fake news classifier to improve the detection performance. Experiments are based on two large scale real-world social media datasets, namely Liar and BuzzFeed. The experimental results show that our model can outperform the accuracy of the state-of-the-art methods by 2.7% and 17.26% on Liar and BuzzFeed, respectively.