[PDF] arxiv.org

AIGCs Confuse AI Too: Investigating and Explaining Synthetic Image-induced Hallucinations in Large Vision-Language Models

Y Gao, J Wang, Z Lin, J Sang - arXiv preprint arXiv:2403.08542, 2024 - arxiv.org
The evolution of Artificial Intelligence Generated Contents (AIGCs) is advancing towards
higher quality. The growing interactions with AIGCs present a new challenge to the data …
被引用次数：1 相关文章 所有 2 个版本
[PDF] arxiv.org

Exploiting Semantic Reconstruction to Mitigate Hallucinations in Vision-Language Models

M Kim, M Kim, J Bae, S Choi, S Kim… - arXiv preprint arXiv …, 2024 - arxiv.org
Hallucinations in vision-language models pose a significant challenge to their reliability,
particularly in the generation of long captions. Current methods fall short of accurately …
相关文章 所有 2 个版本
[PDF] arxiv.org

A survey on hallucination in large vision-language models

H Liu, W Xue, Y Chen, D Chen, X Zhao, K Wang… - arXiv preprint arXiv …, 2024 - arxiv.org
Recent development of Large Vision-Language Models (LVLMs) has attracted growing
attention within the AI landscape for its practical implementation potential. However,`` …
被引用次数：39 相关文章 所有 2 个版本
[PDF] arxiv.org

AUTOHALLUSION: Automatic Generation of Hallucination Benchmarks for Vision-Language Models

X Wu, T Guan, D Li, S Huang, X Liu, X Wang… - arXiv preprint arXiv …, 2024 - arxiv.org
Large vision-language models (LVLMs) hallucinate: certain context cues in an image may
trigger the language module's overconfident and incorrect reasoning on abnormal or …
相关文章
[PDF] arxiv.org

Mitigating hallucinations in large vision-language models with instruction contrastive decoding

X Wang, J Pan, L Ding, C Biemann - arXiv preprint arXiv:2403.18715, 2024 - arxiv.org
Large Vision-Language Models (LVLMs) are increasingly adept at generating contextually
detailed and coherent responses from visual inputs. However, their application in …
被引用次数：7 相关文章 所有 3 个版本
[PDF] arxiv.org

Logical closed loop: Uncovering object hallucinations in large vision-language models

J Wu, Q Liu, D Wang, J Zhang, S Wu, L Wang… - arXiv preprint arXiv …, 2024 - arxiv.org
Object hallucination has been an Achilles' heel which hinders the broader applications of
large vision-language models (LVLMs). Object hallucination refers to the phenomenon that …
被引用次数：6 相关文章 所有 2 个版本
[PDF] arxiv.org

Evaluating the Quality of Hallucination Benchmarks for Large Vision-Language Models

B Yan, J Zhang, Z Yuan, S Shan, X Chen - arXiv preprint arXiv:2406.17115, 2024 - arxiv.org
Despite the rapid progress and outstanding performance of Large Vision-Language Models
(LVLMs) in recent years, LVLMs have been plagued by the issue of hallucination, ie, LVLMs …
相关文章
[PDF] arxiv.org

Analyzing and mitigating object hallucination in large vision-language models

Y Zhou, C Cui, J Yoon, L Zhang, Z Deng, C Finn… - arXiv preprint arXiv …, 2023 - arxiv.org
Large vision-language models (LVLMs) have shown remarkable abilities in understanding
visual information with human languages. However, LVLMs still suffer from object …
被引用次数：75 相关文章 所有 4 个版本
[PDF] arxiv.org

Skip $\textbackslash n $: A simple method to reduce hallucination in Large Vision-Language Models

Z Han, Z Bai, H Mei, Q Xu, C Zhang… - arXiv preprint arXiv …, 2024 - arxiv.org
Recent advancements in large vision-language models (LVLMs) have demonstrated
impressive capability in visual information understanding with human language. Despite …
相关文章 所有 3 个版本
[PDF] arxiv.org

Holistic analysis of hallucination in gpt-4v (ision): Bias and interference challenges

C Cui, Y Zhou, X Yang, S Wu, L Zhang, J Zou… - arXiv preprint arXiv …, 2023 - arxiv.org
While GPT-4V (ision) impressively models both visual and textual information
simultaneously, it's hallucination behavior has not been systematically assessed. To bridge …
被引用次数：37 相关文章 所有 2 个版本