# HumorGen: Cognitive Synergy for Humor Generation in Large Language Models via Persona-Based Distillation

arXiv: https://arxiv.org/abs/2604.09629 · HTML: https://mlsanity.com/paper/2604.09629/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 36 references that are in the map.
- First posted on arXiv 19 Mar 2026.

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

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration](https://mlsanity.com/paper/2307.05300/) (2023)
- [Let's Think Outside the Box: Exploring Leap-of-Thought in Large Language Models with Creative Humor Generation](https://mlsanity.com/paper/2312.02439/) (2023)
- [Delving into RL for Image Generation with CoT: A Study on DPO vs. GRPO](https://mlsanity.com/paper/2505.17017/) (2025)
- [Re-evaluating Automatic LLM System Ranking for Alignment with Human Preference](https://mlsanity.com/paper/2501.00560/) (2024)
- [Can Pre-trained Language Models Understand Chinese Humor?](https://mlsanity.com/paper/2407.04105/) (2024)
- [Innovative Thinking, Infinite Humor: Humor Research of Large Language Models through Structured Thought Leaps](https://mlsanity.com/paper/2410.10370/) (2024)
- [Mixture of Thoughts: Learning to Aggregate What Experts Think, Not Just What They Say](https://mlsanity.com/paper/2509.21164/) (2025)
- [Let's be Humorous: Knowledge Enhanced Humor Generation](https://mlsanity.com/paper/2004.13317/) (2020)
- [Humor Mechanics: Advancing Humor Generation with Multistep Reasoning](https://mlsanity.com/paper/2405.07280/) (2024)
- [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)
- [LOLgorithm: Integrating Semantic,Syntactic and Contextual Elements for Humor Classification](https://mlsanity.com/paper/2408.06335/) (2024)

## Built on by (most cited first, 1 of 1)

- [HumorRank: A Tournament-Based Leaderboard for Evaluating Humor Generation in Large Language Models](https://mlsanity.com/paper/2604.19786/) (2026)

## Abstract (arXiv)

Humor generation poses a significant challenge for Large Language Models (LLMs), because their standard training objective (next-token prediction) inherently conflicts with the surprise and incongruity required for comedy. To bridge this gap, we introduce the Cognitive Synergy Framework, a methodology for generating highquality humor data inspired by psychological theories of humor. Utilizing a Mixtureof-Thought (MoT) approach, we deploy six cognitive personas (e.g., The Absurdist, The Cynic) to synthesize diverse comedic perspectives for a given prompt. This framework produces a theory-grounded dataset, which we use to fine-tune a 7B-parameter student model. We further evaluate two alignment strategies, Direct Preference Optimization (DPO) and an offline group-relative variant O-GRPO, finding that neither improves over SFT. However, our 7B HumorGen model variants significantly outperform larger instruction-tuned baselines and achieve top-tier open-weight performance while remaining competitive with frontier proprietary systems. These results suggest that cognitively driven data curation is more critical than alignment algorithms or model scale for humor generation.