ALGORITHM WATCH:
Article Open access Published: 23 July 2025
Contextualizing ancient texts with generative neural networks
Yannis Assael, Thea Sommerschield, Alison Cooley, Brendan Shillingford, John Pavlopoulos, Priyanka Suresh, Bailey Herms, Justin Grayston, Benjamin Maynard, Nicholas Dietrich, Robbe Wulgaert, Jonathan Prag, Alex Mullen & Shakir Mohamed
Nature (2025)
Abstract
Human history is born in writing. Inscriptions are among the earliest written forms, and offer direct insights into the thought, language and history of ancient civilizations. Historians capture these insights by identifying parallels—inscriptions with shared phrasing, function or cultural setting—to enable the contextualization of texts within broader historical frameworks, and perform key tasks such as restoration and geographical or chronological attribution1. However, current digital methods are restricted to literal matches and narrow historical scopes. Here we introduce Aeneas, a generative neural network for contextualizing ancient texts. Aeneas retrieves textual and contextual parallels, leverages visual inputs, handles arbitrary-length text restoration, and advances the state of the art in key tasks. To evaluate its impact, we conduct a large study with historians using outputs from Aeneas as research starting points. The historians find the parallels retrieved by Aeneas to be useful research starting points in 90% of cases, improving their confidence in key tasks by 44%. Restoration and geographical attribution tasks yielded superior results when historians were paired with Aeneas, outperforming both humans and artificial intelligence alone. For dating, Aeneas achieved a 13-year distance from ground-truth ranges. We demonstrate Aeneas’ contribution to historical workflows through analysis of key traits in the renowned Roman inscription Res Gestae Divi Augusti, showing how integrating science and humanities can create transformative tools to assist historians and advance our understanding of the past.
A well-constructed study of a new AI system that may be quite useful as an aid to human reconstruction and decipherment of ancient inscriptions. It would work best with formulaic inscriptions from a period and language with many surviving examples of similar inscriptions.
For discussion of reconstruction of damaged ancient Hebrew and Aramaic (etc.) texts, with and without AI help, see here and here. Again, this would work best for highly formulaic texts, of which few, but not none, survive in ancient Hebrew or Aramaic. Frank Moore Cross's reconstruction of the Aramaic legal texts (slave conveyances) from the Samaria Papyri come to mind.
Visit PaleoJudaica daily for the latest news on ancient Judaism and the biblical world.