2026
VCE: A ZERO-COST HALLUCINATION MITIGATION METHOD OF LVLMS VIA VISUAL CONTRASTIVE EDITING
ICASSP 2026oral
Large vision-language models (LVLMs) frequently suffer from Object Hallucination (OH), wherein they generate descriptions containing objects that are not actually present in the input image. This phenomenon is particularly problematic in real-world applications such as medical imaging and autonomous…