Li, Z. et al. 2026. SAVER: Mitigating Hallucinations in Large Vision-Language Models via Style-Aware Visual Early Revision. Proceedings of the AAAI Conference on Artificial Intelligence. 40, 42 (Mar. 2026), 35617–35625. DOI:https://doi.org/10.1609/aaai.v40i42.40873.