Identifying artificial intelligence-generated content using the DistilBERT transformer and NLP techniques.

Sci Rep · 2025 · PMC12217667 · PMID 40594720

Europe PMC DOI

hedged sentence

0.0000

closest p · 0.0× alpha

0.0000

boldest claim

The sentences

highly significant− log 10 (p)≈8actually significant

This test also shows that the difference between AI and human text is highly significant (− log 10 (p)≈8, p ≈ 3.69 × 10−9), and it is due to AI text often having less variety in its vocabulary.

also in 132,142 other papers

Quoted from the open-access full text in Europe PMC under the licence the publisher applied. The sentence is reproduced exactly as published; the emphasis is ours.