Why do LLaVA Vision-Language Models Reply to Images in English? Musashi Hinck author Carolin Holtermann author Matthew Lyle Olson author Florian Schneider author Sungduk Yu author Anahita Bhiwandiwalla author Anne Lauscher author Shao-Yen Tseng author Vasudev Lal author 2024-11 text Findings of the Association for Computational Linguistics: EMNLP 2024 Yaser Al-Onaizan editor Mohit Bansal editor Yun-Nung Chen editor Association for Computational Linguistics Miami, Florida, USA conference publication hinck-etal-2024-llava 10.18653/v1/2024.findings-emnlp.783 https://aclanthology.org/2024.findings-emnlp.783/ 2024-11 13402 13421