Re-defining Humor Data Objects for AI Humor Research
This work provides a foundational data object and prompting strategy for AI humor research, but the results are incremental as they primarily improve upon existing LLM prompting techniques.
The authors redefined humor data objects to include context and explanations, and developed an improved LLM prompting method that reduced errors in humor explanation generation, enabling large-scale data synthesis for AI humor research.
In most existing AI humor research, humor was treated as either "present" or "not present." We explore the concept of humor as a social interaction with context and explanations. During this project, we defined a humor reasoning data object and developed a way to prompt LLMs to generate an explanation of humor effective for general population. We iterated from an earlier prompt to an improved prompt, found that the later version reduced important errors, and then scaled generation to a large number of data objects which have the potential to enable data synthesis and data augmentation for AI humor research. Our main takeaway is that better prompting of an LLM improves humor explanation quality, especially by handling missing context, multi-modality, and transcript issues more carefully. These results establish a strong foundation for future work on AI understanding of humor as social behavior.