Briefing: Competency Questions as Executable Plans: a Controlled RAG Architecture for Cultural Heritage Storytelling

The recent publication on ArXiv outlines a framework that employs Large Language Models (LLMs) to enhance storytelling techniques aimed at preserving intangible cultural heritage.

This controlled RAG architecture is designed to systematically manage the complexities involved in generating narratives that reflect collective memory.

The implementation of such a system could significantly impact the way cultural heritage is documented and shared, ensuring that vital stories are not lost over time.