相关论文: Fact-R1: Towards Explainable Video Misinformation …
Recent advancements in Chain of Thought (COT) generation have significantly improved the reasoning capabilities of Large Language Models (LLMs), with reinforcement learning (RL) emerging as an effective post-training approach. Multimodal…
Reinforcement learning has advanced video reasoning in large multi-modal models, yet dominant pipelines either rely on on-policy self-exploration, which plateaus at the model's knowledge boundary, or hybrid replay that mixes policies and…
With the proliferation of Large Language Models (LLMs), the detection of misinformation has become increasingly important and complex. This research proposes an innovative verifiable misinformation detection LLM agent that goes beyond…
Multi-modal fact verification has become an important but challenging issue on social media due to the mismatch between the text and images in the misinformation of news content, which has been addressed by considering cross-modalities to…
The rapid spread of multimodal misinformation on social media calls for more effective and robust detection methods. Recent advances leveraging multimodal large language models (MLLMs) have shown the potential in addressing this challenge.…
Recent studies have demonstrated that incorporating Chain-of-Thought (CoT) reasoning into the detection process can enhance a model's ability to detect synthetic images. However, excessively lengthy reasoning incurs substantial resource…
Fake news threatens democracy and exacerbates the polarization and divisions in society; therefore, accurately detecting online misinformation is the foundation of addressing this issue. We present CrediRAG, the first fake news detection…
Video Large Multimodal Models (VLMMs) have made impressive strides in understanding video content, but they often struggle with abstract and adaptive reasoning-the ability to revise their interpretations when new information emerges. In…
Enhancing the multimodal reasoning capabilities of Multimodal Large Language Models (MLLMs) is a challenging task that has attracted increasing attention in the community. Recently, several studies have applied Reinforcement Learning with…
The rapid dissemination of misinformation through social media increased the importance of automated fact-checking. Furthermore, studies on what deep neural models pay attention to when making predictions have increased in recent years.…
Recent years have witnessed the sustained evolution of misinformation that aims at manipulating public opinions. Unlike traditional rumors or fake news editors who mainly rely on generated and/or counterfeited images, text and videos,…
The rise of multimodal misinformation on social platforms poses significant challenges for individuals and societies. Its increased credibility and broader impact compared to textual misinformation make detection complex, requiring robust…
Charts are essential to data analysis, transforming raw data into clear visual representations that support human decision-making. Although current vision-language models (VLMs) have made significant progress, they continue to struggle with…
Multimodal misinformation increasingly leverages visual persuasion, where repurposed or manipulated images strengthen misleading text. We introduce RW-Post, a post-aligned text--image benchmark for real-world multimodal fact-checking with…
The widespread of false information is a rising concern worldwide with critical social impact, inspiring the emergence of fact-checking organizations to mitigate misinformation dissemination. However, human-driven verification leads to a…
Multimodal LLMs are turning their focus to video benchmarks, however most video benchmarks only provide outcome supervision, with no intermediate or interpretable reasoning steps. This makes it challenging to assess if models are truly able…
Short video platforms have become an important channel for news sharing, but also a new breeding ground for fake news. To mitigate this problem, research of fake news video detection has recently received a lot of attention. Existing works…
Knowledge-Based Visual Question Answering (KB-VQA) requires models to answer questions about an image by integrating external knowledge, posing significant challenges due to noisy retrieval and the structured, encyclopedic nature of the…
Current DeepFake detection scenarios are mostly binary, yet data manipulation can vary across audio, video, or both, whose variability is not captured in binary settings. Four-class audio-visual formulations address this by discriminating…
The rapid development of deepfake video technology has not only facilitated artistic creation but also made it easier to spread misinformation. Traditional deepfake video detection (DVD) methods face issues such as a lack of transparency in…