Explainability and transparency in the realm of digital humanities: toward a historian XAI

Abstract

The recent advancements in the field of Artificial Intelligence (AI) translated to an increased adoption of AI technology in the humanities, which is often challenged by the limited amount of annotated data, as well as its heterogeneity. Despite the scarcity of data it has become common practice to design increasingly complex AI models, usually at the expense of human readability, explainability, and trust. This in turn has led to an increased need for tools to help humanities scholars better explain and validate their models as well as their hypotheses. In this paper, we discuss the importance of employing Explainable AI (XAI) methods within the humanities to gain insights into historical processes as well as ensure model reproducibility and a trustworthy scientific result. To drive our point, we present several representative case studies from the Sphaera project where we analyze a large, well-curated corpus of early modern textbooks using an AI model, and rely on the XAI explanatory outputs to generate historical insights concerning their visual content. More specifically, we show that XAI can be used as a partner when investigating debated subjects in the history of science, such as what strategies were used in the early modern period to showcase mathematical instruments and machines.

Reproducibility and explainability in digital humanities

“…Jon Chun and Katherine Elkins propose an advanced XAI approach and workflow for LLM-based research (GPT-4) using diachronic text sentiment analysis and narrative generation (Chun & Elkins, 2023). Hassan El-Hajj, Oliver Eberle, Anika Merklein et al contribute an equally advanced visual XAI approach for historical research on visual primary sources in the history of science (El-Hajj et al, 2023). Finally, Delfina Sol Martinez Pandiani, Nicolas Lazzari, Marieke van Erp, and Valentina Presutti investigate the mapping of abstract concepts to the technical units of a deep learning model, exploring the potential and limitations of feature visualization as an interpretability technique (Pandiani et al, 2023).…”

“…This special issue, Reproducibility and Explainability in Digital Humanities, was published in two versions: a print version (International Journal of Digital Humanities, 2023a;Burrows, 2023;El-Hajj et al, 2023;Justin & Menon, 2023;Middle, 2023;Schöch, 2023;Siddiqui, 2023;Dobson, 2023;Pandiani et al, 2023;Rudman, 2023;Chun & Elkins, 2023), and an extended online special collection (International Journal of Digital Humanities, 2023b) that features all articles of the print version (a number of them as gold open access publications) plus five additional articles (Joyeux-Prunel, 2023;Huskey, 2023;Blanke et al, 2023;Cooke & Litvack-Katzman, 2023;Hankins, 2023).…”