Guardado en:
Detalles Bibliográficos
Autores principales: Xu, Naen, Sheng, Jiayi, Li, Changjiang, Zhou, Chunyi, Li, Yuyuan, Du, Tianyu, Wang, Jun, Fu, Zhihui, Li, Jinbao, Ji, Shouling
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2604.05930
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914453810839552
author Xu, Naen
Sheng, Jiayi
Li, Changjiang
Zhou, Chunyi
Li, Yuyuan
Du, Tianyu
Wang, Jun
Fu, Zhihui
Li, Jinbao
Ji, Shouling
author_facet Xu, Naen
Sheng, Jiayi
Li, Changjiang
Zhou, Chunyi
Li, Yuyuan
Du, Tianyu
Wang, Jun
Fu, Zhihui
Li, Jinbao
Ji, Shouling
contents Puns are a common form of rhetorical wordplay that exploits polysemy and phonetic similarity to create humor. In multimodal puns, visual and textual elements synergize to ground the literal sense and evoke the figurative meaning simultaneously. Although Vision-Language Models (VLMs) are widely used in multimodal understanding and generation, their ability to understand puns has not been systematically studied due to a scarcity of rigorous benchmarks. To address this, we first propose a multimodal pun generation pipeline. We then introduce MultiPun, a dataset comprising diverse types of puns alongside adversarial non-pun distractors. Our evaluation reveals that most models struggle to distinguish genuine puns from these distractors. Moreover, we propose both prompt-level and model-level strategies to enhance pun comprehension, with an average improvement of 16.5% in F1 scores. Our findings provide valuable insights for developing future VLMs that master the subtleties of human-like humor via cross-modal reasoning.
format Preprint
id arxiv_https___arxiv_org_abs_2604_05930
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle "I See What You Did There": Can Large Vision-Language Models Understand Multimodal Puns?
Xu, Naen
Sheng, Jiayi
Li, Changjiang
Zhou, Chunyi
Li, Yuyuan
Du, Tianyu
Wang, Jun
Fu, Zhihui
Li, Jinbao
Ji, Shouling
Computation and Language
Artificial Intelligence
Puns are a common form of rhetorical wordplay that exploits polysemy and phonetic similarity to create humor. In multimodal puns, visual and textual elements synergize to ground the literal sense and evoke the figurative meaning simultaneously. Although Vision-Language Models (VLMs) are widely used in multimodal understanding and generation, their ability to understand puns has not been systematically studied due to a scarcity of rigorous benchmarks. To address this, we first propose a multimodal pun generation pipeline. We then introduce MultiPun, a dataset comprising diverse types of puns alongside adversarial non-pun distractors. Our evaluation reveals that most models struggle to distinguish genuine puns from these distractors. Moreover, we propose both prompt-level and model-level strategies to enhance pun comprehension, with an average improvement of 16.5% in F1 scores. Our findings provide valuable insights for developing future VLMs that master the subtleties of human-like humor via cross-modal reasoning.
title "I See What You Did There": Can Large Vision-Language Models Understand Multimodal Puns?
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2604.05930