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

2026-04-02

AI Summary

This study addresses the propensity of large language models to generate factual inaccuracies in narratives about intangible cultural heritage by proposing a knowledge graph–based neuro-symbolic architecture. The approach reformulates capability modeling—traditionally used for design verification—as executable narrative plans at runtime, establishing a transparent “plan–retrieve–generate” workflow that ensures evidence closure and full traceability. The system integrates three complementary strategies: symbolic KG-RAG, text-augmented Hybrid-RAG, and structure-aware Graph-RAG. Quantitative evaluation on the Live Aid KG dataset reveals trade-offs among these strategies with respect to factual accuracy, contextual richness, and narrative coherence, offering both methodological insights and practical guidance for generating controllable and trustworthy heritage narratives.

Abstract

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.

Problem

• cultural heritage
• factual accuracy
• hallucination
• storytelling
• veracity

Innovation

• Competency Questions
• Knowledge Graph
• Retrieval-Augmented Generation
• Neuro-symbolic Architecture
• Cultural Heritage Storytelling