Narrative Theory-Driven LLM Methods for Automatic Story Generation and Understanding: A Survey
arXiv:2602.15851v1 Announce Type: cross 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 b
arXiv:2602.15851v1 Announce Type: cross 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.
Executive Summary
This article surveys the application of narrative theories in natural language processing (NLP) using large language models (LLMs) for automatic story generation and understanding. The authors examine the intersection of NLP and narrative studies, proposing a taxonomy for ongoing efforts and highlighting patterns in narrative datasets, tasks, and methodological trends. They argue that instead of pursuing a single benchmark for narrative quality, progress can be made by defining theory-based metrics, conducting large-scale literary analysis, and refining narrative theories through experiments.
Key Points
- ▸ Application of narrative theories in NLP using LLMs
- ▸ Proposed taxonomy for ongoing efforts in narrative studies and NLP
- ▸ Need for theory-based metrics and large-scale literary analysis
Merits
Interdisciplinary Approach
The article highlights the benefits of interdisciplinary collaboration between NLP and narrative studies, enabling the connection of abstract narrative concepts with NLP pipelines.
Demerits
Lack of Unified Benchmark
The article notes that the absence of a unified definition or benchmark for narrative-related tasks makes model comparison difficult, hindering progress in the field.
Expert Commentary
The article provides a comprehensive overview of the current state of narrative theory-driven LLM methods, highlighting the potential benefits and challenges of this approach. The authors' emphasis on the need for theory-based metrics and large-scale literary analysis is well-taken, as it can help to advance our understanding of narrative structures and improve the performance of LLMs in this domain. However, the lack of a unified benchmark for narrative-related tasks remains a significant challenge that must be addressed in future research.
Recommendations
- ✓ Developing theory-based metrics for individual narrative attributes
- ✓ Conducting large-scale, theory-driven literary and social analysis to refine narrative theories
