12/16/2025 | News release | Distributed by Public on 12/16/2025 17:35
Alessandro (Alex) Meregaglia, archivist and associate professor, recently published an article, "Teaching the Limitations of AI in Primary Source Research," in Notes from the Field, an online publication from the Teaching with Primary Sources Collective.
Meregaglia's goal is to equip other primary source instructors with a general overview of the limitations of artificial intelligence so they, in turn, can inform their students. Students might be tempted by AI as an exhaustive tool for primary source research.
With the meteoric rise in popularity of AI and large language models (LLMs), many students have turned to platforms like ChatGPT and Gemini for their research. Even if students aren't using AI to write their papers, they might be using it to gather primary sources and summarize content - erroneously assuming it covers the entire breadth of the internet.
As a primary source instructor, Meregaglia encountered specific limitations of AI to locate and analyze primary sources. For example, AI cannot easily ingest and process PDFs, web archive files, paywalled content, and even open-access structured databases.
The article discusses the current limitations of using AI to search digitized and born digital primary sources - like newspaper databases, the Wayback Machine and archival digital collections. Examples show how AI fails to identify information in these primary sources, even though they are available online and navigable by humans.