From Pixels to Tokens: Revisiting Object Hallucinations in Large Vision-Language Models

• Main Authors: Shang, Yuying, Zeng, Xinyi, Zhu, Yutao, Yang, Xiao, Fang, Zhengwei, Zhang, Jingyuan, Chen, Jiawei, Liu, Zinan, Tian, Yu
• Format: Journal Article
• Language: English
• Published: 09.10.2024
• Subjects: Computer Science - Computation and Language; Computer Science - Computer Vision and Pattern Recognition

Hallucinations in large vision-language models (LVLMs) are a significant challenge, i.e., generating objects that are not presented in the visual input, which impairs their reliability. Recent studies often attribute hallucinations to a lack of understanding of visual input, yet ignore a more fundam...