Humor, a culturally nuanced aspect of human language, poses challenges for
computational understanding and generation, especially in Chinese humor, which
remains relatively unexplored in the NLP community. This paper investigates the
capability of state-of-the-art language models to comprehend and generate
Chinese humor, specifically focusing on training them to create allegorical
sayings. We employ two prominent training methods: fine-tuning a medium-sized
language model and prompting a large one. Our novel fine-tuning approach
incorporates fused Pinyin embeddings to consider homophones and employs
contrastive learning with synthetic hard negatives to distinguish humor
elements. Human-annotated results show that these models can generate humorous
allegorical sayings, with prompting proving to be a practical and effective
method. However, there is still room for improvement in generating allegorical
sayings that match human creativity.

该研究探讨了将最先进的语言模型应用于理解和生成中国幽默的能力，特别关注训练这些模型以创建寓言性语言。针对训练方法，研究采用了两种主要方法：对中型语言模型进行微调和对大型语言模型进行提示。经人工标注结果显示，这些模型能够生成幽默的寓言性语言，提示法证明是一种实用且有效的方法。但在生成能与人类创造力匹配的寓言性语言方面仍有改进的空间。