AIApr 2

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

arXiv:2604.0254534.2h-index: 8
Predicted impact top 64% in AI · last 90 daysOriginality Incremental advance
AI Analysis

This addresses the need for verifiable storytelling in cultural heritage preservation, offering a controlled approach to mitigate LLM hallucinations, though it is incremental in applying existing methods to a specific domain.

The paper tackles the problem of generating factually accurate narratives for cultural heritage by proposing a neuro-symbolic architecture that uses competency questions as executable plans, validated on the Live Aid KG dataset. It finds a trade-off between factual precision, contextual richness, and narrative coherence across three RAG strategies.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes