Disentangling Fact from Sentiment: A Dynamic Conflict-Consensus Framework for Multimodal Fake News Detection

2025-12-19

AI Summary

Existing methods rely on consistency fusion, misinterpreting cross-modal discrepancies—often critical forensic evidence of manipulation—as noise, leading to over-smoothing and dilution of discriminative cues. To address this, we propose a contradiction-driven dynamic conflict-consensus framework. First, we introduce a novel contradiction enhancement paradigm that decouples factual and affective semantic spaces. Second, we design a physics-inspired iterative feature polarization mechanism to explicitly model and amplify subtle cross-modal contradictions. Third, we develop a consensus mechanism integrating local conflict detection with global contextual alignment, enabling synergistic modeling of both contradiction and consistency. Evaluated on three real-world datasets, our method achieves an average accuracy improvement of 3.52% over state-of-the-art approaches. This work provides the first systematic validation that cross-modal contradictions constitute robust, learnable forensic indicators for deepfake detection.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning
• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Prevalent multimodal fake news detection relies on consistency-based fusion, yet this paradigm fundamentally misinterprets critical cross-modal discrepancies as noise, leading to over-smoothing, which dilutes critical evidence of fabrication. Mainstream consistency-based fusion inherently minimizes feature discrepancies to align modalities, yet this approach fundamentally fails because it inadvertently smoothes out the subtle cross-modal contradictions that serve as the primary evidence of fabrication. To address this, we propose the Dynamic Conflict-Consensus Framework (DCCF), an inconsistency-seeking paradigm designed to amplify rather than suppress contradictions. First, DCCF decouples inputs into independent Fact and Sentiment spaces to distinguish objective mismatches from emotional dissonance. Second, we employ physics-inspired feature dynamics to iteratively polarize these representations, actively extracting maximally informative conflicts. Finally, a conflict-consensus mechanism standardizes these local discrepancies against the global context for robust deliberative judgment.Extensive experiments conducted on three real world datasets demonstrate that DCCF consistently outperforms state-of-the-art baselines, achieving an average accuracy improvement of 3.52%.

Problem

• Detects fake news by amplifying cross-modal contradictions
• Separates objective facts from emotional sentiment in multimodal content
• Uses dynamic feature polarization to extract informative conflicts for judgment

Innovation

• Decouples inputs into Fact and Sentiment spaces
• Uses physics-inspired dynamics to polarize representations
• Standardizes local discrepancies against global context