A Pattern-Oriented AI-Powered Approach to Story Composition
摘要
This paper proposes the use of narrative patterns as an effective guide to preserve thematic consistency in the composition of stories using Large Language Models (LLMs). Our approach drove inspiration from a well-accepted, thorough, and overarching classification of folklore types and the deservedly famous Monomyth characterization of heroic quests. The approach comprises both the pattern-guided composition of narratives and the creation of new patterns by applying the most specific generalization (MSG) criterion. We designed and implemented an AI-powered tool to create complex narratives in a storyboard format to demonstrate the feasibility of the proposed approach.