{"ID":2865547,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.22646","arxiv_id":"2509.22646","title":"Learning Human-Perceived Fakeness in AI-Generated Videos via Multimodal LLMs","abstract":"Can humans identify AI-generated (fake) videos and provide grounded reasons? While video generation models have advanced rapidly, a critical dimension -- whether humans can detect deepfake traces within a generated video, i.e., spatiotemporal grounded visual artifacts that reveal a video as machine generated -- has been largely overlooked. We introduce DeeptraceReward, the first fine-grained, spatially- and temporally- aware benchmark that annotates human-perceived fake traces for video generation reward. The dataset comprises 4.3K detailed annotations across 3.3K high-quality generated videos. Each annotation provides a natural-language explanation, pinpoints a bounding-box region containing the perceived trace, and marks precise onset and offset timestamps. We consolidate these annotations into 9 major categories of deepfake traces that lead humans to identify a video as AI-generated, and train multimodal language models (LMs) as reward models to mimic human judgments and localizations. On DeeptraceReward, our 7B reward model outperforms GPT-5 by 34.7% on average across fake clue identification, grounding, and explanation. Interestingly, we observe a consistent difficulty gradient: binary fake v.s. real classification is substantially easier than fine-grained deepfake trace detection; within the latter, performance degrades from natural language explanations (easiest), to spatial grounding, to temporal labeling (hardest). By foregrounding human-perceived deepfake traces, DeeptraceReward provides a rigorous testbed and training signal for socially aware and trustworthy video generation.","short_abstract":"Can humans identify AI-generated (fake) videos and provide grounded reasons? While video generation models have advanced rapidly, a critical dimension -- whether humans can detect deepfake traces within a generated video, i.e., spatiotemporal grounded visual artifacts that reveal a video as machine generated -- has bee...","url_abs":"https://arxiv.org/abs/2509.22646","url_pdf":"https://arxiv.org/pdf/2509.22646v2","authors":"[\"Xingyu Fu\",\"Siyi Liu\",\"Yinuo Xu\",\"Pan Lu\",\"Guangqiuse Hu\",\"Tianbo Yang\",\"Taran Anantasagar\",\"Christopher Shen\",\"Yikai Mao\",\"Yuanzhe Liu\",\"Keyush Shah\",\"Chung Un Lee\",\"Yejin Choi\",\"James Zou\",\"Dan Roth\",\"Chris Callison-Burch\"]","published":"2025-09-26T17:59:54Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\",\"cs.CL\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}