Detecting Computer Generated Text

ZenLabs

Harvard University researchers developing method that identifies computer generated text. The team’s central tenant was whether a system can be built to detect generated text Using that idea, Gehrmann and Strobelt developed a method that, instead of flagging errors in text, identifies text that is too predictable. “The idea we had is that as models get better and better, they go from definitely worse than humans, which is detectable, to as…

Read More