@inproceedings{wang-etal-2025-enhancing, title = "Enhancing Visual-Language Modality Alignment in Large Vision Language Models via Self-Improvement", author = "Wang, Xiyao and Chen, Jiuhai and Wang, Zhaoyang and Zhou, Yuhang and Zhou, Yiyang and Yao, Huaxiu and Zhou, Tianyi and Goldstein, Tom and Bhatia, Parminder and Kass-Hout, Taha and Huang, Furong and Xiao, Cao", editor = "Chiruzzo, Luis and Ritter, Alan and Wang, Lu", booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025", month = apr, year = "2025", address = "Albuquerque, New Mexico", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/fix-sig-urls/2025.findings-naacl.15/", pages = "268--282", ISBN = "979-8-89176-195-7" }