SAVER: Mitigating Hallucinations in Large Vision-Language Models via Style-Aware Visual Early Revision
Zhaoxu Li, Chenqi Kong, Yi Yu, Qiangqiang Wu, Xinghao Jiang, Ngai-Man Cheung, Bihan Wen, Alex Kot
Abstract
Large Vision-Language Models (LVLMs) recently achieve significant breakthroughs in understanding complex visual-textual contexts. However, hallucination issues still limit their real-world applicability. Although previous mitigation methods effectively reduce hallucinations in photographic images, they largely overlook the potential risks posed by stylized images, which play crucial roles in critical scenarios such as game scene understanding, art education, and medical analysis. In this work, we first construct a dataset comprising photographic images and their corresponding stylized versions with carefully annotated caption labels. We then conduct head-to-head comparisons on both discriminative and generative tasks by benchmarking 13 advanced LVLMs on the collected datasets. Our findings reveal that stylized images tend to induce significantly more hallucinations than their photographic counterparts. To address this issue, we propose Style-Aware Visual Early Revision (SAVER), a novel mechanism that dynamically adjusts LVLMs
BibTeX
@inproceedings{aaai2026_savermitigatingh,
title = {SAVER: Mitigating Hallucinations in Large Vision-Language Models via Style-Aware Visual Early Revision},
author = {Zhaoxu Li and Chenqi Kong and Yi Yu and Qiangqiang Wu and Xinghao Jiang and Ngai-Man Cheung and Bihan Wen and Alex Kot and Xudong Jiang},
booktitle = {AAAI 2026},
year = {2026}
}