Mitigating Modality Prior-Induced Hallucinations in Multimodal Large Language Models via Deciphering Attention Causality

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhou, Guanyu, Yan, Yibo, Zou, Xin, Wang, Kun, Liu, Aiwei, Hu, Xuming
Format:	Preprint
Published:	2024
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2410.04780