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

ACL ARR 2026 March Submission1241 Authors

Keywords: Humor generation, Large Language Models, Cognitive Personas

Abstract: Humor generation poses a significant challenge for Large Language Models (LLMs), because their standard training objective—predicting the most likely next word—inherently conflicts with the surprise and incongruity needed for comedy. To bridge this gap, we introduce the Cognitive Synergy Framework, a theoretically grounded methodology for generating high quality humor data inspired by psychological theories of humor. Utilizing a Mixture of-Thought (MoT) approach, we deployed six cognitive personas (e.g., The Absurdist, The Cynic) to synthesize diverse comedic perspectives for a given prompt. This framework creates a theoretically grounded dataset, which we use to fine-tune a 7B parameter student model. We compare Direct Preference Optimization (DPO) and a novel Offline Group Relative Policy Optimization (O-GRPO); our 7B model significantly outperforms larger instruction-tuned baselines and achieves performance competitive with state-of-the art proprietary models. We find that cognitive-driven data curation is far more critical than alignment algorithms or model scale for humor generation.

Paper Type: Long

Research Area: Generation

Research Area Keywords: Cognitive Modeling, Generation, automatic evaluation, human evaluation, text-to-text generation

Contribution Types: NLP engineering experiment, Publicly available software and/or pre-trained models, Data analysis

Languages Studied: English

Submission Number: 1241