The evolution of Artificial Intelligence Generated Contents (AIGCs) is advancing towards higher quality. The growing interactions with AIGCs present a new challenge to the data-driven AI community: While AI-generated contents have played a crucial role in a wide range of AI models, the potential hidden risks they introduce have not been thoroughly examined. Beyond human-oriented forgery detection, AI-generated content poses potential issues for AI models originally designed to process natural data. In this study, we underscore the exacerbated hallucination phenomena in Large Vision-Language Models (LVLMs) caused by AI-synthetic images. Remarkably, our findings shed light on a consistent AIGC \textbf{hallucination bias}: the object hallucinations induced by synthetic images are characterized by a greater quantity and a more uniform position distribution, even these synthetic images do not manifest unrealistic or additional relevant visual features compared to natural images. Moreover, our investigations on Q-former and Linear projector reveal that synthetic images may present token deviations after visual projection, thereby amplifying the hallucination bias.

翻译：人工智能生成内容（AIGC）正朝着更高质量的方向演进。随着人类与AIGC互动日益频繁，这给数据驱动的AI领域带来了新挑战：尽管AIGC已在众多AI模型中发挥关键作用，但其引入的潜在隐藏风险尚未得到充分探究。除了面向人类的伪造检测外，AI生成内容还可能对原本设计用于处理自然数据的AI模型构成潜在问题。在本研究中，我们着重强调了由AI合成图像引发的大视觉语言模型（LVLMs）中更为严重的幻觉现象。值得注意的是，我们的研究揭示了一致性的AIGC幻觉偏差：与自然图像相比，即使合成图像并未表现出不真实或额外的相关视觉特征，其引发的物体幻觉在数量上更多，且位置分布更均匀。此外，我们对Q-Former和线性投影器的研究表明，合成图像在视觉投影后可能产生token偏差，从而放大了这种幻觉偏差。