Lune

ACL Findings2025

BottleHumor: Self-Informed Humor Explanation using the Information Bottleneck Principle

Eunjeong Hwang, Peter West, Vered Shwartz

Abstract

Humor is prevalent in online communications and it often relies on more than one modality (e.g., cartoons and memes). Interpreting humor in multimodal settings requires drawing on diverse types of knowledge, including metaphorical, sociocultural, and commonsense knowledge. However, identifying the most useful knowledge remains an open question. We introduce BOTTLEHUMOR, a method inspired by the information bottleneck principle that elicits relevant world knowledge from vision and language models which is iteratively refined for generating an explanation of the humor in an unsupervised manner. Our experiments on three datasets confirm the advantage of our method over a range of baselines. Our method can further be adapted in the future for additional tasks that can benefit from eliciting and conditioning on relevant world knowledge and open new research avenues in this direction.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

1 top-tier paper has cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers1

  1. Assessing the Capabilities of LLMs in Humor: A Multi-dimensional Analysis of Oogiri Generation and EvaluationRitsu Sakabe, Hwichan Kim, Tosho Hirasawa, Mamoru KomachiAAAI 2026

Builds on19

  1. Self-Refine: Iterative Refinement with Self-FeedbackAman Madaan, Niket Tandon, Prakhar Gupta, Skyler Hallinan et al.NeurIPS 2023 · 4,972 citations
  2. Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question AnsweringPan Lu, Swaroop Mishra, Tanglin Xia, Liang Qiu et al.NeurIPS 2022 · 2,727 citations
  3. Visual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language ModelsYushi Hu, Weijia Shi, Xingyu Fu, Dan Roth et al.NeurIPS 2024 · 373 citations
  4. Graph Information BottleneckTailin Wu, Hongyu Ren, Pan Li, Jure LeskovecNeurIPS 2020 · 366 citations
  5. How Does Information Bottleneck Help Deep Learning?Kenji Kawaguchi, Zhun Deng, Xu Ji, Jiaoyang HuangICML 2023 · 117 citations

Related papers

  1. Humor Knowledge Enriched Transformer for Understanding Multimodal HumorMd. Kamrul Hasan, Sangwu Lee, Wasifur Rahman, Amir Zadeh et al.AAAI 2021 · 98 citations
  2. On the Wings of Imagination: Conflicting Script-based Multi-role Framework for Humor Caption GenerationWenbo Shang, Yuxi Sun, Jing Ma, Xin HuangICLR 2026 · 3 citations
  3. PunchBench: Benchmarking MLLMs in Multimodal Punchline ComprehensionKun Ouyang, Yuanxin Liu, Shicheng Li, Yi Liu et al.ACL 2025 · 3 citations
  4. "I See What You Did There": Can Large Vision-Language Models Understand Multimodal Puns?Naen Xu, Jiayi Sheng, Changjiang Li, Chunyi Zhou et al.ACL 2026 · 1 citation
  5. MEMEX: Detecting Explanatory Evidence for Memes via Knowledge-Enriched ContextualizationShivam Sharma, Ramaneswaran S., Udit Arora, Md. Shad Akhtar et al.ACL 2023 · 2 citations
Dusk over the sea between two cliffs drawn in fine vertical lines