Tootfinder

CMIE: Combining MLLM Insights with External Evidence for Explainable Out-of-Context Misinformation Detection
Fanxiao Li, Jiaying Wu, Canyuan He, Wei Zhou
https://arxiv.org/abs/2505.23449

CMIE: Combining MLLM Insights with External Evidence for Explainable Out-of-Context Misinformation Detection
Multimodal large language models (MLLMs) have demonstrated impressive capabilities in visual reasoning and text generation. While previous studies have explored the application of MLLM for detecting out-of-context (OOC) misinformation, our empirical analysis reveals two persisting challenges of this paradigm. Evaluating the representative GPT-4o model on direct reasoning and evidence augmented reasoning, results indicate that MLLM struggle to capture the deeper relationships-specifically, cases…