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

arXiv: https://arxiv.org/abs/2511.21732 · HTML: https://mlsanity.com/paper/2511.21732/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 17 of its 47 references that are in the map.
- First posted on arXiv 21 Nov 2025.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)

## Builds on (most cited first, 17 of 17)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [A Survey on Multimodal Large Language Models for Autonomous Driving](https://mlsanity.com/paper/2311.12320/) (2023)
- [The Revolution of Multimodal Large Language Models: A Survey](https://mlsanity.com/paper/2402.12451/) (2024)
- [Efficient Multimodal Large Language Models: A Survey](https://mlsanity.com/paper/2405.10739/) (2024)
- [A Survey of State of the Art Large Vision Language Models: Alignment, Benchmark, Evaluations and Challenges](https://mlsanity.com/paper/2501.02189/) (2025)
- [Humor Detection: A Transformer Gets the Last Laugh](https://mlsanity.com/paper/1909.00252/) (2019)
- [A Survey on Evaluation of Multimodal Large Language Models](https://mlsanity.com/paper/2408.15769/) (2024)
- [A Comprehensive Survey and Guide to Multimodal Large Language Models in Vision-Language Tasks](https://mlsanity.com/paper/2411.06284/) (2024)
- [Meta Learning to Bridge Vision and Language Models for Multimodal Few-Shot Learning](https://mlsanity.com/paper/2302.14794/) (2023)
- [Personalized Multimodal Large Language Models: A Survey](https://mlsanity.com/paper/2412.02142/) (2024)
- [Enhancing Few-Shot Vision-Language Classification with Large Multimodal Model Features](https://mlsanity.com/paper/2412.00142/) (2024)
- [memeBot: Towards Automatic Image Meme Generation](https://mlsanity.com/paper/2004.14571/) (2020)
- [AI Humor Generation: Cognitive, Social and Creative Skills for Effective Humor](https://mlsanity.com/paper/2502.07981/) (2025)
- [A Survey of Generative Categories and Techniques in Multimodal Generative Models](https://mlsanity.com/paper/2506.10016/) (2025)
- [How to Bridge the Gap between Modalities: Survey on Multimodal Large Language Model](https://mlsanity.com/paper/2311.07594/) (2023)

## Built on by (most cited first, 4 of 4)

- [MER-Bench: A Comprehensive Benchmark for Multimodal Meme Reappraisal](https://mlsanity.com/paper/2603.15020/) (2026)
- [Culture-Aware Humorous Captioning: Multimodal Humor Generation across Cultural Contexts](https://mlsanity.com/paper/2604.18091/) (2026)
- [Computational Humor with Multimodal LLMs: Methods, Datasets, Evaluation, and Challenges](https://mlsanity.com/paper/2607.19011/) (2026)
- [Towards High-Level Semantic Intelligence](https://mlsanity.com/paper/2607.24082/) (2026)

## Abstract (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, theories of humor suggest that it follows learnable patterns and structures, making it theoretically possible for generative models to acquire them implicitly. In recent years, multimodal humor has become a prevalent form of online communication, especially among Gen Z, highlighting the need for AI systems capable of integrating visual understanding with humorous language generation. However, existing data-driven approaches lack explicit modeling or theoretical grounding of humor, often producing literal descriptions that fail to capture its underlying cognitive mechanisms, resulting in the generated image descriptions that are fluent but lack genuine humor or cognitive depth. To address this limitation, we propose HUMORCHAIN (HUmor-guided Multi-step Orchestrated Reasoning Chain for Image Captioning), a theory-guided multi-stage reasoning framework. It integrates visual semantic parsing, humor- and psychology-based reasoning, and a fine-tuned discriminator for humor evaluation, forming an interpretable and controllable cognitive reasoning chain. To the best of our knowledge, this is the first work to explicitly embed cognitive structures from humor theories into multimodal humor generation, enabling a structured reasoning process from visual understanding to humor creation. Experiments on Meme-Image-No-Text, Oogiri-GO, and OxfordTVG-HIC datasets show that HUMORCHAIN outperforms state-of-the-art baselines in human humor preference, Elo/BT scores, and semantic diversity, demonstrating that theory-driven structured reasoning enables large language models to generate humor aligned with human perception.