Editors’ Summary: This post considers how historians can make use of LLMs and NLP without flattening the individual stories that make up history. In the author’s words: “the challenge is how to do that without losing sensitivity to individual lives, how to move from large-scale datasets to arguments about trends like the rise of nonviolence without flattening culture, decision, and imagination into mere counts.” The post lays out a historical methodology for using large datasets and models without losing detail.
Editors’ Choice: Beyond Cherry-Picking: Scaling Historical Arguments
