No existing research shows state-of-the-art AI detectors are racially biased, researcher says

TuhinChakr · x · 2026-11-17

Tuhin Chakrabarty, a researcher who studies AI writing, discussed bias in AI text detectors in a thread. He noted there is no dearth of remarkably talented African authors whose books should obviously not be flagged—and if detectors did flag them, such technology ought to be burned to the ground. However, to his knowledge, no extant research shows that state-of-the-art AI detection programs are racially biased. In an earlier tweet in the thread, he plotted the "Blue Fighter" against 187 books plus ShyGirl and DaggerMouth, finding that Negative Parallelism and Trailing Participle Tails tell a relatively clear story, along with word density patterns.

Related event: Debate over AI text detection bias flares as scholars question accuracy(2 posts)→

Original post →

More from Safety

Safety channel →