When ‘YES’ Meets ‘BUT’: Can Large Models Comprehend Contradictory Humor Through Comparative Reasoning?
Published in arXiv preprint, 2025
We extend YesBut to 1,262 multilingual and multicultural comics and study comparative reasoning, visual perception, hallucination, and social-knowledge augmentation in large language and vision-language models.
Recommended citation: Tuo Liang, Zhe Hu, Jing Li, Hao Zhang, Yiren Lu, Yunlai Zhou, Yiran Qiao, Disheng Liu, Jeirui Peng, Jing Ma, and Yu Yin. "When 'YES' Meets 'BUT': Can Large Models Comprehend Contradictory Humor Through Comparative Reasoning?" arXiv:2503.23137, 2025.
Download Paper
