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

arXiv: https://arxiv.org/abs/2502.18331 · HTML: https://mlsanity.com/paper/2502.18331/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 57 references that are in the map.
- First posted on arXiv 22 Feb 2025.

## Builds on (most cited first, 29 of 29)

- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering](https://mlsanity.com/paper/2209.09513/) (2022)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge](https://mlsanity.com/paper/2410.02736/) (2024)
- [Visual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language Models](https://mlsanity.com/paper/2406.09403/) (2024)
- [Towards Multimodal Sarcasm Detection (An _Obviously_ Perfect Paper)](https://mlsanity.com/paper/1906.01815/) (2019)
- [Graph Information Bottleneck](https://mlsanity.com/paper/2010.12811/) (2020)
- [Unsupervised Commonsense Question Answering with Self-Talk](https://mlsanity.com/paper/2004.05483/) (2020)
- [UR-FUNNY: A Multimodal Language Dataset for Understanding Humor](https://mlsanity.com/paper/1904.06618/) (2019)
- [Reframing Human-AI Collaboration for Generating Free-Text Explanations](https://mlsanity.com/paper/2112.08674/) (2021)
- [Do Androids Laugh at Electric Sheep? Humor "Understanding" Benchmarks from The New Yorker Caption Contest](https://mlsanity.com/paper/2209.06293/) (2022)
- [How Does Information Bottleneck Help Deep Learning?](https://mlsanity.com/paper/2305.18887/) (2023)
- [KAM-CoT: Knowledge Augmented Multimodal Chain-of-Thoughts Reasoning](https://mlsanity.com/paper/2401.12863/) (2024)
- [Multimodal Information Bottleneck: Learning Minimal Sufficient Unimodal and Multimodal Representations](https://mlsanity.com/paper/2210.17444/) (2022)
- [MemeCap: A Dataset for Captioning and Interpreting Memes](https://mlsanity.com/paper/2305.13703/) (2023)
- [Molecular Facts: Desiderata for Decontextualization in LLM Fact Verification](https://mlsanity.com/paper/2406.20079/) (2024)
- [TokenSHAP: Interpreting Large Language Models with Monte Carlo Shapley Value Estimation](https://mlsanity.com/paper/2407.10114/) (2024)
- [Compressive Visual Representations](https://mlsanity.com/paper/2109.12909/) (2021)
- [BottleSum: Unsupervised and Self-supervised Sentence Summarization using the Information Bottleneck Principle](https://mlsanity.com/paper/1909.07405/) (2019)
- [Reverse Engineering Self-Supervised Learning](https://mlsanity.com/paper/2305.15614/) (2023)
- [SMILE: Multimodal Dataset for Understanding Laughter in Video with Language Models](https://mlsanity.com/paper/2312.09818/) (2023)
- [Deductive Closure Training of Language Models for Coherence, Accuracy, and Updatability](https://mlsanity.com/paper/2401.08574/) (2024)
- [Natural Language Decompositions of Implicit Content Enable Better Text Representations](https://mlsanity.com/paper/2305.14583/) (2023)
- [Understanding Figurative Meaning through Explainable Visual Entailment](https://mlsanity.com/paper/2405.01474/) (2024)
- [We Are Humor Beings: Understanding and Predicting Visual Humor](https://mlsanity.com/paper/1512.04407/) (2015)
- [Dynamic Multimodal Information Bottleneck for Multimodality Classification](https://mlsanity.com/paper/2311.01066/) (2023)
- [Leveraging Information Bottleneck for Scientific Document Summarization](https://mlsanity.com/paper/2110.01280/) (2021)
- [Cracking the Code of Juxtaposition: Can AI Models Understand the Humorous Contradictions](https://mlsanity.com/paper/2405.19088/) (2024)
- [Locating Information Gaps and Narrative Inconsistencies Across Languages: A Case Study of LGBT People Portrayals on Wikipedia](https://mlsanity.com/paper/2410.04282/) (2024)

## Built on by (most cited first, 6 of 6)

- [Large Language Models for Subjective Language Understanding: A Survey](https://mlsanity.com/paper/2508.07959/) (2025)
- [SWI: Speaking with Intent in Large Language Models](https://mlsanity.com/paper/2503.21544/) (2025)
- [Culture-Aware Humorous Captioning: Multimodal Humor Generation across Cultural Contexts](https://mlsanity.com/paper/2604.18091/) (2026)
- [Grounded Satirical Generation with RAG](https://mlsanity.com/paper/2605.10853/) (2026)
- [Computational Humor with Multimodal LLMs: Methods, Datasets, Evaluation, and Challenges](https://mlsanity.com/paper/2607.19011/) (2026)
- [Towards High-Level Semantic Intelligence](https://mlsanity.com/paper/2607.24082/) (2026)

## Abstract (arXiv)

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 method, 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.