Artificial Epanorthosis: Why large language models overuse a classical rhetorical figure, and how to mitigate it
Why AI keeps awkwardly correcting itself, and how to fix it
Large language models systematically overuse epanorthosis—a rhetorical trick where speakers correct themselves mid-sentence, like "This is not a course. It is a journey of transformation." The habit stems from training on promotional writing and reward signals that favor confident, emphatic phrasing. Researchers measured this quirk across different model sizes and writing genres, finding models use the figure about twice as often as humans in formal speech, but rarely in casual conversation—and developed simple techniques that cut the overuse by 50 to 75 percent.
As AI writing becomes more prevalent, models risk reshaping human writing style rather than the other way around. The misalignment between how AI and humans naturally write could gradually shift our own rhetorical habits if we normalize machine-generated text as a standard. The techniques demonstrated here—lightweight fixes that tune models to human baselines per genre—show that calibration, not elimination, is the practical goal: AI should match human style, not define it.