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.

人工智能生成内容的进化朝着更高质量的方向发展，与人工智能生成内容的不断交互给数据驱动的人工智能社区带来了新的挑战：尽管AI生成的内容在广泛的AI模型中扮演着关键角色，但它们引入的潜在风险尚未得到充分的审查。本研究突出了由AI合成图像引起的大型视觉语言模型中的严重幻觉现象，结果发现合成图像引起的物体幻觉特点是数量更多且位置分布更均匀，即使这些合成图像与自然图像相比没有呈现非现实或额外相关的视觉特征。此外，我们对Q-former和线性投影仪的研究发现，视觉投影后合成图像可能呈现令牌偏差，从而放大幻觉偏差。

AIGCs对AI的混淆：探究和解释大型视觉语言模型中由合成图像引起的幻觉