VIB-Probe: Detecting and Mitigating Hallucinations in Vision-Language Models via Variational Information Bottleneck

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Feiran, Wu, Yixin, Wang, Zhenghua, Wang, Xiaohua, Lv, Changze, Huang, Xuanjing, Zheng, Xiaoqing
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2601.05547