arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2306.13195cs.CLcs.AI

向GPT-3提示:用于幽默生成的逐步思考指令

Prompt to GPT-3: Step-by-Step Thinking Instructions for Humor Generation

Rensselaer Polytechnic Institute(伦斯勒理工学院)

Yuetian Chen, Bowen Shi, Mei Si

AI总结:

本文针对GPT-3在理解用户等复杂任务中的局限性,通过建模人类喜剧写作理论并利用逐步思考指令来生成幽默,同时探讨了认知距离在创造幽默中的作用。

摘要:

人工智能在自然语言处理方面取得显著进展,GPT-3等模型展现出令人印象深刻的能力。然而,在处理需要理解用户的复杂任务(如掌握人类喜剧写作策略)时,这些模型仍存在局限性。本文通过建模人类喜剧写作理论并利用逐步思考指令,探索使用GPT-3进行幽默生成。此外,我们还探讨了认知距离在创造幽默中的作用。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑