Co-creation of AI technology, empowering curators of cultural heritage information and guarding research commons

TY - CHAP

T1 - Co-creation of AI technology, empowering curators of cultural heritage information and guarding research commons

AU - Scharnhorst, Andrea

AU - Yang, Han

AU - Touber, Jetze

AU - Ferguson, Kim

AU - Mayr, Philipp

AU - Tykhonov, Vyacheslav

N1 - 30 pages, chapter in the book Understanding Science with Large Language Models? (pp. 383-412). transcript. Edited by Arno Simons, Adrian Wüthrich, Michael Zichert, Gerd Graßhoff (eds.)

PY - 2026/5/27

Y1 - 2026/5/27

N2 - The substance of this paper is the description of the use of Retrieval-Augmented Generation (RAG) for specific digital collections of cultural assets. The collections are provided by institutions operating in the cultural sector. The topical areas are the humanities and social sciences. More concretely, most of the work presented here was enabled by a European-funded research project MuseIT which is clearly situated in the realm of fostering new technologies for Cultural Heritage. We adhere to this interaction by presenting a sequence of our experimentations. This sequence is narrated as a specific journey of engineering all executed around a specific data-sharing and archiving platform Dataverse. Implementing a local chatbot for collections - a method also known as RAG in Information Retrieval - is the current culmination of this journey. The engineering journey we describe in the core of the paper starts from "archives for everyone" and ends with "local chatbots for specific collections".

AB - The substance of this paper is the description of the use of Retrieval-Augmented Generation (RAG) for specific digital collections of cultural assets. The collections are provided by institutions operating in the cultural sector. The topical areas are the humanities and social sciences. More concretely, most of the work presented here was enabled by a European-funded research project MuseIT which is clearly situated in the realm of fostering new technologies for Cultural Heritage. We adhere to this interaction by presenting a sequence of our experimentations. This sequence is narrated as a specific journey of engineering all executed around a specific data-sharing and archiving platform Dataverse. Implementing a local chatbot for collections - a method also known as RAG in Information Retrieval - is the current culmination of this journey. The engineering journey we describe in the core of the paper starts from "archives for everyone" and ends with "local chatbots for specific collections".

KW - cs.DL

UR - https://www.transcript-verlag.de/978-3-8376-7994-6/understanding-science-with-large-language-models/

U2 - 10.48550/arXiv.2605.28481

DO - 10.48550/arXiv.2605.28481

M3 - Chapter

SN - 978-3-8376-7994-6

SP - 383

BT - Understanding Science with Large Language Models?

A2 - Simons, Arno

A2 - Wüthrich, Adrian

A2 - Zichert, Michael

A2 - Graßhoff, Gerd

PB - Transcript Verlag

T2 - Large Language Models for the History, Philosophy, and Sociology of Science

Y2 - 2 April 2025 through 4 April 2025

ER -