GPT detectors biased against non-native English writers

A recently published, peer-reviewed paper shows researchers (all from Stanford University’s Department of Computer Science and Department of Electrical Engineering) found that programs built to detect whether text was generated by AI or humans would more often falsely label it as AI-generated when it was written by non-native English writers, reports Maria Diaz on ZDNet.

“Our current recommendation is that we should be extremely careful about and maybe try to avoid using these detectors as much as possible,” said senior author James Zou, from Stanford University.