Large language models (LLMs) are increasingly used as knowledge discovery tools. Humanistic disciplines like historical linguistics and literary studies have shown interest in this capability. These fields often construct arguments on the basis of distinctions between phenomena like time-period or genre. Such methodological investments complicate reliance on LLMs pretrained over large sets of broadly-collected data. We show that efficient pretraining techniques produce useful models of semantic change over modest historical corpora without allowing potential contamination from anachronistic data. We verify that these trained-from-scratch models better respect historical divisions and are more computationally efficient compared to the standard approach of fine-tuning an existing LLM. We compare the trade-offs in general linguistic fluency versus detecting and characterizing various forms of linguistic change, and provide a pipeline implementation of our approach that can be readily adapted and applied to a wide range of diachronic phenomena.

This paper presents AnnoPlot, a web application designed to analyze, manage, and visualize annotated text data.Users can configure projects, upload datasets, and explore their data through interactive visualization of span annotations with scatter plots, clusters, and statistics. AnnoPlot supports various transformer models to compute high-dimensional embeddings of text annotations and utilizes dimensionality reduction algorithms to offer users a novel 2D view of their datasets.A dynamic approach to dimensionality reduction allows users to adjust visualizations in real-time, facilitating category reorganization and error identification. The proposed application is open-source, promoting transparency and user control.Especially suited for the Digital Humanities, AnnoPlot offers a novel solution to address challenges in dynamic annotation datasets, empowering users to enhance data integrity and adapt to evolving categorizations.