Computational Humor with Multimodal LLMs: Methods, Datasets, Evaluation, and Challenges
Summary
This survey examines computational humor understanding in multimodal LLMs, covering methods, datasets, evaluation protocols, and challenges such as shortcut-prone evaluation and weak evidence grounding.
View Cached Full Text
Cached at: 07/22/26, 10:42 AM
Paper page - Computational Humor with Multimodal LLMs: Methods, Datasets, Evaluation, and Challenges
Source: https://huggingface.co/papers/2607.19011
Abstract
Multimodalhumorinmemes,cartoons,andcomicsremainsdifficultforAIsystemsbecauseintendedmeaningdependsonnon-literalmechanisms,sharedculturalknowledge,andcommunicativeintentratherthanliteralscenedescription.Thissurveyfocusesonvisualhumorunderstandinginsingle-imageandmulti-panelartifacts,whiletreatinghumorgenerationasanemergingdownstreamfrontier.Wepositiontheliteratureagainstpriorhumor,sarcasm,andgeneralMLLMsurveysandorganizeitusingacapability-centrichierarchyspanningrecognition,interpretationandreasoning,andgeneration.Underthislens,wesynthesizebenchmarkdesign,evaluationprotocols,andmodelingparadigms,tracingthefield’sshiftfromtask-specificfusionmodelstolarge-modelapproachesbasedonmultimodalalignment,evidence-groundedreasoning,andcontrolledgeneration.Weconcludebyhighlightingthemainbarrierstoprogress:shortcut-proneevaluation,limitedculturalandnarrativecoverage,weakevidencegrounding,andunresolvedsafetyandownershipconcerns.
View arXiv pageView PDFAdd to collection
Get this paper in your agent:
hf papers read 2607\.19011
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2607.19011 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2607.19011 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2607.19011 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
Computational Humor with Multimodal LLMs: Methods, Datasets, Evaluation, and Challenges
A comprehensive survey on multimodal humor understanding using large language models, covering methods, datasets, evaluation protocols, and challenges in interpreting humor in memes, cartoons, and comics.
i built a benchmark to test whether LLMs can understand and create jokes
A developer built a benchmark called lolbench to evaluate LLMs on understanding and creating jokes, revealing models are strong at explaining real jokes but struggle with failed ones, and incorporating human voting for preference testing.
HumorRank: A Tournament-Based Leaderboard for Evaluating Humor Generation in Large Language Models
HumorRank introduces a tournament-based leaderboard using pairwise evaluations and Bradley-Terry MLE to rank LLMs on humor generation, showing humor quality depends on comedic mastery rather than scale.
Multiplication in Multimodal LLMs: Computation with Text, Image, and Audio Inputs
This paper investigates the arithmetic limitations of multimodal LLMs on multi-digit multiplication across text, image, and audio modalities, introducing a controlled benchmark and a novel 'arithmetic load' metric (C) that better predicts model accuracy than traditional step-counting methods. Results show accuracy collapses as C grows, and that performance degradation is primarily computational rather than perceptual.
MultiHuSE: A Multimodal Dataset for Humour Styles and Emotions
This paper introduces MultiHuSE, a multimodal dataset comprising videos of actors with annotations for humour styles and emotions. Baseline experiments show that multimodal fusion improves humour style classification accuracy over unimodal approaches.