AI not yet good enough to grade university essays, rewarding 'style over substance'
Researchers have used top Generative AI models to grade hundreds of undergraduate essays and found that AI only matched human-awarded degree classification around half the time, with AI often failing to accurately assess the best and worst submissions.
Image: Phys.org
Researchers have used top Generative AI models to grade hundreds of undergraduate essays and found that AI only matched human-awarded degree classification around half the time, with AI often failing to accurately assess the best and worst submissions.
Originally published at Phys.org
