Author name: Junru Song, Yimeng Hu, Yijing Chen, Huining Li, Qian Li, Lizhen Cui, Yuntao Du

arXiv:2604.26419v1 Announce Type: cross
Abstract: Large Vision-Language Models (VLMs) have achieved remarkable multimodal performance yet remain prone to factual hallucinations, particularly in long-tail or specialized domains. Moreover, current model…