Google DeepMind and UPenn build AI text detectors that show their work
Photo: Crypto Briefing
A new pipeline turns black-box detectors into readable classifiers while holding onto most of their accuracy AI text detectors already help decide who gets into a school, whose paper survives peer review, and which posts stay online. Most of them cannot explain a single decision they make. A research team from Google DeepMind and the University of Pennsylvania wants to change that. Their new method turns an opaque detector into one that reasons in concepts a human can read, and the accuracy cost is surprisingly small.
Source: Crypto Briefing
