@article{burnafterreadingdomultimodallarge, title = {Burn After Reading: Do Multimodal Large Language Models Truly Capture Order of Events in Image Sequences?}, author = {Yingjin Song and Yupei Du and Denis Paperno and Albert Gatt}, year = {2025}, eprint = {2506.10415}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2506.10415v1}, }