서사 구조를 따르는 LLM 기반 스토리 생성 연구

LLM-Based Story Generation Aligned with Narrative Structure

초록

This study proposes a structured story generation system based on traditional narrative theory using a large language model (LLM). The proposed system sequentially constructs a three-act structure and a 15-step narrative structure of "Save the Cat!" based on the log line, character information, and genre input by the user, and each step is embodied through hierarchical generation and prompt chaining. In particular, when user modifications occur, the changes are designed to be automatically reflected in the upper and lower stages to maintain narrative consistency and logic. To verify the effectiveness of this system, human-written narratives, single-prompt-based generative narratives, and generative narratives from the proposed system were compared and evaluated, yielding excellent results in terms of narrative structure fidelity and logic. By demonstrating the structural controllability of LLM-based story generation, this study suggests applicability in the field of digital content production in the future.

키워드

Large Language Models; Story Generation; Narrative Structure; Prompt Chaining; Hierarchical Story Generation; 대형 언어 모델; 스토리 생성; 내러티브 구조; 프롬프트 체이닝; 계층적 스토리 생성
제목
서사 구조를 따르는 LLM 기반 스토리 생성 연구
제목 (타언어)
LLM-Based Story Generation Aligned with Narrative Structure
저자
지은수; 유태경
발행일
2025-07
유형
Y
저널명
한국컴퓨터게임학회논문지
권
38
호
3
페이지
61 ~ 72