An international team of researchers is using artificial intelligence to illuminate one of the oldest mysteries in literary history: who wrote the Bible. The sacred text is a complex tapestry woven from different traditions over hundreds of years. This new study combines statistical analysis with biblical expertise to distinguish between the unique writing styles of its various contributors.

This graph plots biblical chapters based on linguistic style, sorting them into Deuteronomistic (D, yellow), Deuteronomistic History (DtrH, blue), and Priestly (P, green) traditions.

(Faigenbaum-Golovin et al., 2025)

The team’s method focuses on subtle, unconscious linguistic habits that serve as an author’s fingerprint. They trained a novel AI model to analyze word frequencies in the Enneateuch, the first nine books of the Hebrew Bible. The AI learned to differentiate between major scribal traditions by analyzing texts with well-established authorship.

The model confirmed that the writing styles of the Deuteronomy and Deuteronomistic History corpora are more similar to each other than to the Priestly writings. More revealingly, it found that the two parts of the Ark Narrative, previously considered a single story, were likely written by different authors. A key advantage is the AI’s ability to explain its reasoning by specifying the words that led to its conclusions.

This new approach provides a powerful and objective tool that complements traditional methods of biblical scholarship. Researchers believe the methodology has applications far beyond ancient religious texts and could be used to verify the authenticity of other historical documents, from the Dead Sea Scrolls to letters attributed to figures like Abraham Lincoln.