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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Barla, Naga Sowjanya, de Berardinis, Jacopo
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911564356911104
author Barla, Naga Sowjanya
de Berardinis, Jacopo
author_facet Barla, Naga Sowjanya
de Berardinis, Jacopo
contents The preservation of intangible cultural heritage is a critical challenge as collective memory fades over time. While Large Language Models (LLMs) offer a promising avenue for generating engaging narratives, their propensity for factual inaccuracies or "hallucinations" makes them unreliable for heritage applications where veracity is a central requirement. To address this, we propose a novel neuro-symbolic architecture grounded in Knowledge Graphs (KGs) that establishes a transparent "plan-retrieve-generate" workflow for story generation. A key novelty of our approach is the repurposing of competency questions (CQs) - traditionally design-time validation artifacts - into run-time executable narrative plans. This approach bridges the gap between high-level user personas and atomic knowledge retrieval, ensuring that generation is evidence-closed and fully auditable. We validate this architecture using a new resource: the Live Aid KG, a multimodal dataset aligning 1985 concert data with the Music Meta Ontology and linking to external multimedia assets. We present a systematic comparative evaluation of three distinct Retrieval-Augmented Generation (RAG) strategies over this graph: a purely symbolic KG-RAG, a text-enriched Hybrid-RAG, and a structure-aware Graph-RAG. Our experiments reveal a quantifiable trade-off between the factual precision of symbolic retrieval, the contextual richness of hybrid methods, and the narrative coherence of graph-based traversal. Our findings offer actionable insights for designing personalised and controllable storytelling systems.
format Preprint
id arxiv_https___arxiv_org_abs_2604_02545
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Competency Questions as Executable Plans: a Controlled RAG Architecture for Cultural Heritage Storytelling
Barla, Naga Sowjanya
de Berardinis, Jacopo
Artificial Intelligence
The preservation of intangible cultural heritage is a critical challenge as collective memory fades over time. While Large Language Models (LLMs) offer a promising avenue for generating engaging narratives, their propensity for factual inaccuracies or "hallucinations" makes them unreliable for heritage applications where veracity is a central requirement. To address this, we propose a novel neuro-symbolic architecture grounded in Knowledge Graphs (KGs) that establishes a transparent "plan-retrieve-generate" workflow for story generation. A key novelty of our approach is the repurposing of competency questions (CQs) - traditionally design-time validation artifacts - into run-time executable narrative plans. This approach bridges the gap between high-level user personas and atomic knowledge retrieval, ensuring that generation is evidence-closed and fully auditable. We validate this architecture using a new resource: the Live Aid KG, a multimodal dataset aligning 1985 concert data with the Music Meta Ontology and linking to external multimedia assets. We present a systematic comparative evaluation of three distinct Retrieval-Augmented Generation (RAG) strategies over this graph: a purely symbolic KG-RAG, a text-enriched Hybrid-RAG, and a structure-aware Graph-RAG. Our experiments reveal a quantifiable trade-off between the factual precision of symbolic retrieval, the contextual richness of hybrid methods, and the narrative coherence of graph-based traversal. Our findings offer actionable insights for designing personalised and controllable storytelling systems.
title Competency Questions as Executable Plans: a Controlled RAG Architecture for Cultural Heritage Storytelling
topic Artificial Intelligence
url https://arxiv.org/abs/2604.02545