Documenting AI use in humanities research

Presentation at HumInfra 2025 conference in Stockholm.

Abstract

This paper explores the critical need to document the use of Artificial Intelligence (AI) in humanities research. While AI offers efficiency and analytical power, its application raises concerns about transparency, bias, and reproducibility. Existing documentation frameworks often emphasise technical aspects, overlooking the human and contextual dimensions vital to humanities scholarship. Drawing on cross-disciplinary literature, the paper advocates for integrating paradata (process-related meta-information) to capture both technical and human facets of AI use. It proposes shifting the focus from speculative future needs to documenting the transformation AI is intended to achieve within specific research contexts. Practical strategies include combining automated tools with reflective documentation practices and providing clear explanations of the purpose and expected outcomes of AI use. The paper calls for infrastructural support and a rethinking of documentation sufficiency to enhance understanding, reuse, and accountability in humanities research.