| title | Computational Humor with Multimodal LLMs: Methods, Datasets, Evaluation, and Challenges |
|---|---|
| authors | Tuo Liang, Zhe Hu, Disheng Liu, Jing Li, Yu Yin |
| date | 2026-07-21 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2607.19011 |
| upvotes | 3 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf |
| abstract | Multimodal humor in memes, cartoons, and comics remains difficult for AI systems because intended meaning depends on non-literal mechanisms, shared cultural knowledge, and communicative intent rather than literal scene description. This survey focuses on visual humor understanding in single-image and multi-panel artifacts, while treating humor generation as an emerging downstream frontier. We position the literature against prior humor, sarcasm, and general MLLM surveys and organize it using a capability-centric hierarchy spanning recognition, interpretation and reasoning, and generation. Under this lens, we synthesize benchmark design, evaluation protocols, and modeling paradigms, tracing the field's shift from task-specific fusion models to large-model approaches based on multimodal alignment, evidence-grounded reasoning, and controlled generation. We conclude by highlighting the main barriers to progress: shortcut-prone evaluation, limited cultural and narrative coverage, weak evidence grounding, and unresolved safety and ownership concerns. |
cite
@misc{liang2026computational,
title={Computational Humor with Multimodal LLMs: Methods, Datasets, Evaluation, and Challenges},
author={Tuo Liang and Zhe Hu and Disheng Liu and Jing Li and Yu Yin},
year={2026},
eprint={2607.19011},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2607.19011}
}