Reproduce “Co-creation of AI technology, empowering curators of cultural heritage information and guarding research commons” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Andrea Scharnhorst, Han Yang, Jetze Touber, Kim Ferguson, Philipp Mayr, Vyacheslav Tykhonov
This paper details the practical implementation of Retrieval-Augmented Generation (RAG) technology in cultural heritage institutions, utilizing a local chatbot for the European-funded MuseIT project. It showcases how public sector entities can actively co-create AI solutions to improve interaction with digital cultural assets, aligning with Open Science principles and guarding research commons.
Key insights
- Public sector cultural heritage institutions can effectively co-create AI technology through interdisciplinary collaboration, developing solutions that align with public values, transparency, and specific domain requirements.
- Semantic enrichment of digital collections through tailored metadata schemes and integration with Knowledge Organisation Systems (KOS) is fundamental for enabling effective and meaningful RAG implementation.
- Implementing AI solutions like RAG chatbots locally offers public sector institutions greater control over data, enhanced model transparency, and reduces dependence on proprietary commercial models.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.