Generative AI in Heritage Practice
Improving the Accessibility of Heritage Guidance
Bibliographic Data
| ID | 13124695 |
|---|---|
| Authors | Jessica Witte (0000-0003-1144-8065, University of Edinburgh, corresponding author), Edmund Lee (0000-0002-1166-0878, Historic England), Lisa Brausem (Historic England), Verity Shillabeer (Historic England), Chiara Bonacchi (0000-0002-0872-0614, University of Edinburgh) |
| Year | 2025 |
| Volume | 8 |
| Issue | 12 |
| Pages | 513-513 |
| Publication date | 2025-12-06 |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | Heritage (JOURNAL) |
| Journal identifiers | ISSN: 2571-9408 • E-ISSN: 2571-9408 |
| Publisher | MDPI AG (PUBLISHER • IT) |
| DOI | 10.3390/heritage8120513 |
| OpenAlex | W4417114490 |
| Language | EN |
| Citations received | 2 |
| References cited | 96 |
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
Chatbot · Cultural heritage · Generative grammar · Generative model · Relation (database · AI in Service Interactions · Artificial Intelligence in Healthcare and Education · Spreadsheets and End-User Computing
The AI Mirror
Uses of Heritage
Generative AI enhances individual creativity but reduces the collective diversity of novel content
ChatGPT
The Uncanny Valley [From the Field]
A new readability yardstick.
Prompt Engineering with ChatGPT
Minds, brains, and programs
Why general artificial intelligence will not be realized
The Effects of Generative AI Platforms on Undergraduates’ Narrative Intelligence and Writing Self-Efficacy
Graduate students’ use of ChatGPT for academic text revision
ChatGPT and the potential growing of ghost bibliographic references
A Preliminary Investigation of Fake Peer-Reviewed Citations and References Generated by ChatGPT
Impacts of artificial intelligence on carbon emissions in China
Affective neuroscience theory and attitudes towards artificial intelligence
Why we should have seen that coming
Understanding the application of handwritten text recognition technology in heritage contexts
Large Language Models and Generative AI, Oh My
Into the language of museum audio descriptions
Monitoring Looting at Cultural Heritage Sites
Assessing Readability
Digital heritage research re-theorised
The linguistic assumptions underlying readability formulae
| Citations per year | 2 |
|---|---|
| Citation span | 2026 - 2026 (1) |
| Highly cited | No |