CORE: Conflict-Oriented Reasoning for General Multimodal Manipulation Detection
Quick Take
The CORE framework enhances multimodal large language models (MLLMs) with conflict detection capabilities, leveraging the Conflict Attribution Corpus (CAC) for robust generalization to new manipulation types. Extensive experiments show CORE outperforms existing state-of-the-art models, adapting effectively even in zero-shot scenarios.
Key Points
- CORE uses the Conflict Attribution Corpus for fine-grained conflict annotations.
- It achieves robust conflict detection with minimal data requirements.
- The framework adapts to unseen manipulation types effectively.
- Extensive experiments validate CORE's superiority over existing models.
- Dataset and code are publicly available for further research.
Article Content
From source RSS / original summaryarXiv:2606. 03066v1 Announce Type: new Abstract: The rapid rise of generative AI has made multimodal fake news increasingly realistic and pervasive, posing severe threats to public trust and social stability. Existing detection methods rely heavily on manipulation-specific models and large-scale labeled data, resulting in poor generalization to emerging manipulation types. We observed that the essence of manipulated misinformation lies in its intrinsic conflicts, \textbf{i. e.
,} semantic or physical inconsistencies either across modalities or with common world knowledge. Inspired by this observation, we propose \textbf{C}onflict-\textbf{O}riented \textbf{RE}asoning (\textbf{CORE}) framework, an effective paradigm that learns to endows multimodal large language models (MLLMs) with explicit conflict-capturing capability.
To this end, CORE first constructs the Conflict Attribution Corpus (CAC) with fine-grained annotations of conflict factors and sources, providing essential data support for subsequent conflict perception training. By performing conflict-oriented representation enhancement and reasoning based on CAC, CORE achieves robust and generalizable conflict detection, effectively and rapidly adapting to unseen manipulation types with a few samples or in even zero-shot settings.
Extensive experiments demonstrate that CORE surpasses state-of-the-art models. The dataset and code are publicly available at https://github. com/shen8424/CORE.
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →AUDITFLOW: Executable Symbolic Environments for Structured Financial Reporting Verification
AuditFlow introduces a multi-agent framework for structured financial reporting verification, achieving 82.09% accuracy with GPT-5.5, outperforming the baseline by 14.93 points. It utilizes a symbolic environment for effective audit processes, demonstrating the necessity of deterministic checks for reliable verification.
