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

arXiv:2604.09629 · cs.CL · Submitted 2026-03-19 · Read on arXiv

cs.CL

Submitted: 2026-03-19

Updated: 2026-09-12

Comments: Accepted at EMNLP 2026 Main Conference

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• GRPO — 59× in this paper · explained in 6 episodes
• Alignment — 26× in this paper · explained in 1 episode
• Benchmark — 19× in this paper · explained in 2 episodes
• Trace — 14× in this paper · explained in 2 episodes
• Distillation — 9× in this paper · explained in 2 episodes
• Humor Transfer Bench — 9× in this paper
• Pairwise Comparisons — 9× in this paper · explained in 2 episodes
• Adaptation — 7× in this paper · explained in 1 episode
• Reasoning Traces — 7× in this paper · explained in 3 episodes
• Direct Preference Optimization — 6× in this paper
• Fine-Tuning — 6× in this paper · explained in 5 episodes
• Supervised Fine-Tuning — 5× in this paper
• Direct Preference Optimization (DPO) — 4× in this paper · explained in 9 episodes
• LLM judge — 4× in this paper · explained in 2 episodes
• Supervised Fine-Tuning (SFT) — 4× in this paper · explained in 8 episodes
• Mode Collapse — 3× in this paper · explained in 2 episodes
• Ablation — 2× in this paper · explained in 1 episode
• Annotator Agreement — 2× in this paper · explained in 1 episode
• Cognitive Synergy Distillation — 2× in this paper
• Consistency — 2× in this paper · explained in 3 episodes
• Core — 2× in this paper · explained in 2 episodes
• GRPO Objective — 2× in this paper · explained in 2 episodes
• Generalization — 2× in this paper · explained in 13 episodes
• Group Relative Policy Optimization — 2× in this paper
• Instruction Tuning — 2× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 2× in this paper · explained in 6 episodes
• Scaffolding — 2× in this paper · explained in 3 episodes
• alpha — 2× in this paper · explained in 1 episode
• Accuracy — 1× in this paper · explained in 1 episode
• Alignment Tax — 1× in this paper · explained in 4 episodes
• Catastrophic Forgetting — 1× in this paper · explained in 5 episodes
• Chain-of-Thought (CoT) — 1× in this paper · explained in 4 episodes
• Creative Leap of Thought — 1× in this paper
• Domain Shift — 1× in this paper · explained in 4 episodes
• Generalizability — 1× in this paper · explained in 6 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• Group Relative Policy Optimization (GRPO) — 1× in this paper · explained in 5 episodes
• Interpretability — 1× in this paper · explained in 15 episodes
• Perplexity — 1× in this paper · explained in 3 episodes
• Provenance — 1× in this paper · explained in 4 episodes

Sources

• HumorRank: A Tournament-Based Leaderboard for Evaluating Humor Generation in Large Language Models
• Mixture of Thoughts: Learning to Aggregate What Experts Think, Not Just What They Say
• ChatGPT is fun, but it is not funny! Humor is still challenging Large Language Models
• LOLgorithm: Integrating Semantic,Syntactic and Contextual Elements for Humor Classification
• Not All Jokes Land: Evaluating Large Language Models Understanding of Workplace Humor
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• Humor Mechanics: Advancing Humor Generation with Multistep Reasoning
• Delving into RL for Image Generation with CoT: A Study on DPO vs. GRPO
• CleanComedy: Creating Friendly Humor through Generative Techniques
• Innovative Thinking, Infinite Humor: Humor Research of Large Language Models through Structured Thought Leaps
• Let's be Humorous: Knowledge Enhanced Humor Generation

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering