@inproceedings{kamath-etal-2023-whats, title = "What`s {\textquotedblleft}up{\textquotedblright} with vision-language models? Investigating their struggle with spatial reasoning", author = "Kamath, Amita and Hessel, Jack and Chang, Kai-Wei", editor = "Bouamor, Houda and Pino, Juan and Bali, Kalika", booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing", month = dec, year = "2023", address = "Singapore", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2023.emnlp-main.568/", doi = "10.18653/v1/2023.emnlp-main.568", pages = "9161--9175" }