# Humor Mechanics: Advancing Humor Generation with Multistep Reasoning

arXiv: https://arxiv.org/abs/2405.07280 · HTML: https://mlsanity.com/paper/2405.07280/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 40 references that are in the map.
- First posted on arXiv 12 May 2024.

## Builds on (most cited first, 14 of 14)

- [Compositionality decomposed: how do neural networks generalise?](https://mlsanity.com/paper/1908.08351/) (2019)
- [The Quantization Model of Neural Scaling](https://mlsanity.com/paper/2303.13506/) (2023)
- [A Theory for Emergence of Complex Skills in Language Models](https://mlsanity.com/paper/2307.15936/) (2023)
- [Do Androids Laugh at Electric Sheep? Humor "Understanding" Benchmarks from The New Yorker Caption Contest](https://mlsanity.com/paper/2209.06293/) (2022)
- [Humor Detection: A Transformer Gets the Last Laugh](https://mlsanity.com/paper/1909.00252/) (2019)
- [ExPUNations: Augmenting Puns with Keywords and Explanations](https://mlsanity.com/paper/2210.13513/) (2022)
- [Can AI Be as Creative as Humans?](https://mlsanity.com/paper/2401.01623/) (2024)
- [The Iron(ic) Melting Pot: Reviewing Human Evaluation in Humour, Irony and Sarcasm Generation](https://mlsanity.com/paper/2311.05552/) (2023)
- [Paranoid Transformer: Reading Narrative of Madness as Computational Approach to Creativity](https://mlsanity.com/paper/2007.06290/) (2020)
- [Witscript 3: A Hybrid AI System for Improvising Jokes in a Conversation](https://mlsanity.com/paper/2301.02695/) (2023)
- [Prompt to GPT-3: Step-by-Step Thinking Instructions for Humor Generation](https://mlsanity.com/paper/2306.13195/) (2023)
- [Post Turing: Mapping the landscape of LLM Evaluation](https://mlsanity.com/paper/2311.02049/) (2023)
- [Witscript: A System for Generating Improvised Jokes in a Conversation](https://mlsanity.com/paper/2302.02008/) (2023)
- [Witscript 2: A System for Generating Improvised Jokes Without Wordplay](https://mlsanity.com/paper/2302.03036/) (2023)

## Built on by (most cited first, 8 of 8)

- [HumorReject: Decoupling LLM Safety from Refusal Prefix via A Little Humor](https://mlsanity.com/paper/2501.13677/) (2025)
- [Not All Jokes Land: Evaluating Large Language Models Understanding of Workplace Humor](https://mlsanity.com/paper/2506.01819/) (2025)
- [CleanComedy: Creating Friendly Humor through Generative Techniques](https://mlsanity.com/paper/2412.09203/) (2024)
- [The truth is no diaper: Human and AI-generated associations to emotional words](https://mlsanity.com/paper/2511.04077/) (2025)
- [HumorGen: Cognitive Synergy for Humor Generation in Large Language Models via Persona-Based Distillation](https://mlsanity.com/paper/2604.09629/) (2026)
- ["Not Human, Funnier": How Machine Identity Shapes Humor Perception in Online AI Stand-up Comedy](https://mlsanity.com/paper/2602.12763/) (2026)
- [lmfaoooo at SemEval-2026 Task 1: Humor Is an Audience. Preference Modeling for Constrained Humor Generation](https://mlsanity.com/paper/2606.00022/) (2026)
- [Computational Humor with Multimodal LLMs: Methods, Datasets, Evaluation, and Challenges](https://mlsanity.com/paper/2607.19011/) (2026)

## Abstract (arXiv)

In this paper, we explore the generation of one-liner jokes through multi-step reasoning. Our work involved reconstructing the process behind creating humorous one-liners and developing a working prototype for humor generation. We conducted comprehensive experiments with human participants to evaluate our approach, comparing it with human-created jokes, zero-shot GPT-4 generated humor, and other baselines. The evaluation focused on the quality of humor produced, using human labeling as a benchmark. Our findings demonstrate that the multi-step reasoning approach consistently improves the quality of generated humor. We present the results and share the datasets used in our experiments, offering insights into enhancing humor generation with artificial intelligence.