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.

错误:搜索内容不能为空,请输入英文关键词
错误:关键词超出字数限制,请精简
高级检索

A Pattern-Oriented AI-Powered Approach to Story Composition

  • Edirlei Soares de Lima,
  • Margot M. E. Neggers,
  • Marco A. Casanova,
  • Bruno Feijó,
  • Antonio L. Furtado

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.