paper-with-me

홈 › Papers

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

2026-03-19 · Edward Ajayi, Prasenjit Mitra 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.

📄 PDF Abstract BibTeX arXiv:2604.09629

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

HUMORCHAIN: Theory-Guided Multi-Stage Reasoning for Interpretable Multimodal Humor Generation

2025-11-21 · Jiajun Zhang, Shijia Luo, Ruikang Zhang, Qi Su arxiv

Humor, as both a creative human activity and a social binding mechanism, has long posed a major challenge for AI generation. Although producing humor requires complex cognitive reasoning and social understanding, theorie…

Image CaptioningSemantic Parsing

Is This a Joke? Detecting Humor in Spanish Tweets

2017-03-28 · Santiago Castro, Matías Cubero, Diego Garat, Guillermo Moncecchi

While humor has been historically studied from a psychological, cognitive and linguistic standpoint, its study from a computational perspective is an area yet to be explored in Computational Linguistics. There exist some…

Humor Detection

Prompt to GPT-3: Step-by-Step Thinking Instructions for Humor Generation

2023-06-22 · Yuetian Chen, Bowen Shi, Mei Si

Artificial intelligence has made significant progress in natural language processing, with models like GPT-3 demonstrating impressive capabilities. However, these models still have limitations when it comes to complex ta…

A funny companion: Distinct neural responses to perceived AI- versus human-generated humor

2025-09-13 · Xiaohui Rao, Hanlin Wu, Zhenguang G. Cai arxiv

As AI companions become capable of human-like communication, including telling jokes, understanding how people cognitively and emotionally respond to AI humor becomes increasingly important. This study used electroenceph…

OxfordTVG-HIC: Can Machine Make Humorous Captions from Images?

2023-07-21 · ICCV 2023 1 · Runjia Li, Shuyang Sun, Mohamed Elhoseiny, Philip Torr

This paper presents OxfordTVG-HIC (Humorous Image Captions), a large-scale dataset for humour generation and understanding. Humour is an abstract, subjective, and context-dependent cognitive construct involving several c…

DiversityImage Captioning