Researcher finds negative parallelism and participle tails as AI writing tells across 187 books

TuhinChakr · x · 2026-11-18

TuhinChakr, who studies AI writing, plotted a work against 187 books plus controls, finding that Negative Parallelism and Trailing Participle Tails tell a relatively clear story (with caveats); word density differences were also notable. The quoted thread lists these features as tells for detecting AI-generated writing.

Original post →

More from Research

Research channel →