@article{visitbenchabenchmarkforvisionlanguage, title = {VisIT-Bench: A Benchmark for Vision-Language Instruction Following Inspired by Real-World Use}, author = {Yonatan Bitton and Hritik Bansal and Jack Hessel and Rulin Shao and Wanrong Zhu and Anas Awadalla and Josh Gardner and Rohan Taori and Ludwig Schmidt}, year = {2023}, eprint = {2308.06595}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2308.06595v4}, }