NYU and UT Austin researchers identify six language patterns in AI text that reduce readability
Researchers from NYU and the University of Texas at Austin analyzed outputs from 14 language models across 120 conversations, 45 coding sessions, and 980 essays. They found that models systematically overuse six sentence structures rare in human writing, such as noun stacking, nominalization, and subject-verb separation.
Return to original text
A short introduction is retained here; the full text from the source website is not reposted. For specific wording and subsequent updates, please refer to the original article.
Open AIHOT original