Dynamic narrative generation: Integrating retrieval-augmented generation with large language models for enhanced storytelling systems
Abstract
We present an AI storytelling system that fuses Retrieval-Augmented Generation (RAG) and Large Language Models (LLMs) within a coherent, personalized narrative system. The architecture comprises the use of MongoDB for narrative data storage, Pinecone and ColBERT-XM for semantic retrieval, and ‘Llama 3.3-70B’ for creating the story. It proposes a novel graph-based system for mapping character relationships to maintain narrative consistency between different sections. Evaluation through an interactive web platform shows significant improvement in character consistency and genre adaptability over the baseline systems. User feedback data points to engagement being significantly higher and validates the system’s effectiveness towards entertainment and educational endeavours. Our work takes further steps toward advancing AI-powered creative content generation by giving rise to a scalable framework embedding state-of-the-art NLP methods into structured data management.
Read the paper
Related studies
- Knowledge Management Perspective of Generative Artificial Intelligence
- Navigating Generative Artificial Intelligence Promises and Perils for Knowledge and Creative Work
- Characterizing the evolving research on enterprise content management
- Large language models and multimodal foundation models for precision oncology
- From Generative AI to Extended Reality: Multidisciplinary Perspectives on the Challenges, Opportunities, and Future of Educational Computing
- Generative Artificial Intelligence: A New Engine for Advancing Environmental Science and Engineering
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.