Prompt to GPT-3: Step-by-Step Thinking Instructions for Humor Generation
Yuetian Chen, Bowen Shi, Mei Si
TL;DR
This paper investigates enhancing GPT-3's humor generation by applying step-by-step reasoning and modeling human comedy strategies, emphasizing the importance of cognitive distance in creating humorous content.
Contribution
It introduces a novel approach combining structured thinking instructions with humor theory to improve AI-generated comedy, a relatively unexplored area.
Findings
Step-by-step instructions improve humor quality.
Modeling human comedy strategies enhances AI humor generation.
Cognitive distance plays a key role in humor creation.
Abstract
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 tasks that require an understanding of the user, such as mastering human comedy writing strategies. This paper explores humor generation using GPT-3 by modeling human comedy writing theory and leveraging step-by-step thinking instructions. In addition, we explore the role of cognitive distance in creating humor.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsHumor Studies and Applications · Artificial Intelligence in Games · Language, Metaphor, and Cognition
MethodsAttention Is All You Need · Refunds@Expedia|||How do I get a full refund from Expedia? · Adam · Byte Pair Encoding · Residual Connection · Weight Decay · Softmax · Dropout · Attention Dropout · Dense Connections