Problem
Research questions and friction points this paper is trying to address.
narrative theory
large language models
story generation
story understanding
narratology
Narrative Theory-Driven LLM Methods for Automatic Story Generation and Understanding: A Survey
🤖 AI Summary
This study addresses the lack of systematic narrative-theoretic grounding in current research on automatic story generation and comprehension, noting a pronounced lag in handling nonfictional narratives and multi-level modeling compared to understanding tasks. Drawing on classical narratological frameworks—particularly the distinction between story and discourse levels—the work provides the first systematic review of large language models’ application to narrative tasks, uncovering critical gaps in data diversity, depth of theoretical integration, and task balance. Its primary contribution is a theory-driven, fine-grained evaluation framework that moves beyond monolithic “narrative quality” metrics toward a multidimensional, narratologically informed assessment paradigm. The paper further proposes a comprehensive research roadmap to advance cross-domain narrative analysis and context-aware story generation.
📝 Abstract
Applications of narrative theories using large language models (LLMs) deliver promising use-cases in automatic story generation and understanding tasks. Our survey examines how natural language processing (NLP) research engages with fields of narrative studies, and proposes a taxonomy for ongoing efforts that reflect established distinctions in narratology. We discover patterns in the following: narrative datasets and tasks, narrative theories and NLP pipeline and methodological trends in prompting and fine-tuning. We highlight how LLMs enable easy connections of NLP pipelines with abstract narrative concepts and opportunities for interdisciplinary collaboration. Challenges remain in attempts to work towards any unified definition or benchmark of narrative related tasks, making model comparison difficult. For future directions, instead of the pursuit of a single, generalised benchmark for'narrative quality', we believe that progress benefits more from efforts that focus on the following: defining and improving theory-based metrics for individual narrative attributes to incrementally improve model performance; conducting large-scale, theory-driven literary/social/cultural analysis; and creating experiments where outputs can be used to validate or refine narrative theories. This work provides a contextual foundation for more systematic and theoretically informed narrative research in NLP by providing an overview to ongoing research efforts and the broader narrative studies landscape.
Innovation
Methods, ideas, or system contributions that make the work stand out.
narrative theory
large language models
story generation
story understanding
narratology
🔎 Similar Papers
No similar papers found.
