EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Generative AI in Heritage Practice: Improving the Accessibility of Heritage Guidance

Jessica Witte, Edmund Lee, Lisa Brausem, Verity Shillabeer, Chiara Bonacchi

Heritage · 06.12.2025 · 8 (12) · 513

DOI: 10.3390/heritage8120513 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Heritage, online erschienen am 06.12.2025. Verfasst von Jessica Witte und 4 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 162 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Historic England’s Digital Strategy Board Innovation Fund.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper discusses the potential for integrating Generative Artificial Intelligence (GenAI) into professional heritage practice with the aim of enhancing the accessibility of public-facing guidance documents. We developed HAZEL, a GenAI chatbot fine-tuned to assist with revising written guidance relating to heritage conservation and interpretation. Using quantitative assessments, we compare HAZEL’s performance to that of ChatGPT (GPT-4) in a series of tasks related to the guidance writing process. The results of this comparison indicate a slightly better performance of HAZEL over ChatGPT, suggesting that the GenAI chatbot is more effective once the underlying large language model (LLM) has been fine-tuned. However, we also note significant limitations, particularly in areas requiring cultural sensitivity and more advanced technical expertise. These findings suggest that, while GenAI cannot replace human heritage professionals in technical authoring tasks, its potential to automate and expedite certain aspects of guidance writing could offer valuable benefits to heritage organisations, especially in resource-constrained contexts.

Förderung

  • Historic England’s Digital Strategy Board Innovation Fund

Zitieren

APA

Witte, J., Lee, E., Brausem, L., Shillabeer, V., & Bonacchi, C. (2025). Generative AI in Heritage Practice: Improving the Accessibility of Heritage Guidance. Heritage, 8(12), 513. https://doi.org/10.3390/heritage8120513

Vancouver

Witte J, Lee E, Brausem L, Shillabeer V, Bonacchi C. Generative AI in Heritage Practice: Improving the Accessibility of Heritage Guidance. Heritage. 2025;8(12):513. doi:10.3390/heritage8120513

BibTeX
@article{Witte2025,
  author = {Witte, Jessica and Lee, Edmund and Brausem, Lisa and Shillabeer, Verity and Bonacchi, Chiara},
  title = {Generative AI in Heritage Practice: Improving the Accessibility of Heritage Guidance},
  journal = {Heritage},
  year = {2025},
  volume = {8},
  number = {12},
  pages = {513},
  doi = {10.3390/heritage8120513}
}
Kostenlos starten →