Can Large Vision-Language Models Understand Multimodal Sarcasm?

@inproceedings{wang-2025-large, author = {Xinyu Wang and Yue Zhang and Liqiang Jing}, editor = {Meeyoung Cha and Carl Yang and Senjuti Basu Roy and Chanyoung Park and Zhenhui Jessie Li and Noseong Park and Carl Yang and Senjuti Basu Roy and Zhenhui Jessie Li and Jaap Kamps and Kijung Shin and Bryan Hooi and Lifang He}, title = {{Can Large Vision-Language Models Understand Multimodal Sarcasm?}}, booktitle = {{Proceedings of the 34th ACM International Conference on Information and Knowledge Management, CIKM 2025, Seoul, Republic of Korea, November 10-14, 2025}}, pages = {5340--5345}, publisher = {ACM}, year = {2025}, url = {https://doi.org/10.1145/3746252.3760864}, doi = {https://doi.org/10.1145/3746252.3760864} }