ACL Findings2024
Are U a Joke Master? Pun Generation via Multi-Stage Curriculum Learning towards a Humor LLM
Yang Chen, Chong Yang, Tu Hu, Xinhao Chen, Man Lan, Li Cai, Xinlin Zhuang, Xuan Lin, Xin Lu, Aimin Zhou
Abstract
Although large language models (LLMs) acquire extensive world knowledge and some reasoning abilities, their proficiency in generating humorous sentences remains a challenge. Previous research has demonstrated that the humor generation capabilities of ChatGPT are confined to producing merely 25 unique jokes. In this work, we concentrate on endowing LLMs with the ability of generating puns, a particular category of humor by preference learning method. We propose a multistage curriculum preference learning framework to optimize both pun structure preferences and humor preferences. Specifically, we improve the Direct Preference Optimization (DPO) algorithm to address the challenge of multi-objective alignment problem. Besides, to facilitate further advancement in this field, we collect a Chinese Pun (ChinesePun) dataset, containing 2.1k puns and corresponding annotations. Experimental results on both Chinese and English benchmark datasets demonstrate that our method significantly outperforms all the baseline models.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
3 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
Cited by top-tier papers3
- On the Wings of Imagination: Conflicting Script-based Multi-role Framework for Humor Caption GenerationWenbo Shang, Yuxi Sun, Jing Ma, Xin HuangICLR 2026 · 3 citations
- Assessing the Capabilities of LLMs in Humor: A Multi-dimensional Analysis of Oogiri Generation and EvaluationRitsu Sakabe, Hwichan Kim, Tosho Hirasawa, Mamoru KomachiAAAI 2026
- Phun-Bench: Evaluating LLMs on Phonological Understanding in ChineseXing Yue, Yongliang Shen, Weiming LuACL 2026
Builds on10
- Training language models to follow instructions with human feedbackLong Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida et al.NeurIPS 2022 · 24,707 citations
- LoRA: Low-Rank Adaptation of Large Language ModelsEdward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu et al.ICLR 2022 · 18,833 citations
- Direct Preference Optimization: Your Language Model is Secretly a Reward ModelRafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D. Manning et al.NeurIPS 2023 · 10,924 citations
- Revisiting Pre-Trained Models for Chinese Natural Language ProcessingYiming Cui, Wanxiang Che, Ting Liu, Bing Qin et al.EMNLP Findings 2020 · 866 citations
- Defining and Characterizing Reward GamingJoar Skalse, Nikolaus H. R. Howe, Dmitrii Krasheninnikov, David KruegerNeurIPS 2022 · 466 citations
Related papers
- "A good pun is its own reword": Can Large Language Models Understand Puns?Zhijun Xu, Siyu Yuan, Lingjie Chen, Deqing YangEMNLP 2024 · 6 citations
- Talk Funny! A Large-Scale Humor Response Dataset with Chain-of-Humor InterpretationYuyan Chen, Yichen Yuan, Panjun Liu, Dayiheng Liu et al.AAAI 2024 · 34 citations
- "What do you call a dog that is incontrovertibly true? Dogma": Testing LLM Generalization through HumorAlessio Cocchieri, Luca Ragazzi, Paolo Italiani, Giuseppe Tagliavini et al.ACL 2025
- "I See What You Did There": Can Large Vision-Language Models Understand Multimodal Puns?Naen Xu, Jiayi Sheng, Changjiang Li, Chunyi Zhou et al.ACL 2026 · 1 citation
- Can Language Models Make Fun? A Case Study in Chinese Comical CrosstalkJianquan Li, Xiangbo Wu, Xiaokang Liu, Qianqian Xie et al.ACL 2023 · 2 citations
