New AI tool detects ChatGPT-generated scientific papers with 99% accuracy.

Researchers from the University of Kansas have developed an algorithm that can detect scientific papers generated by ChatGPT with over 99% accuracy. The team compiled datasets to train and test the algorithm to classify papers written by scientists and by ChatGPT. The classifier was able to discern between real science writing from humans and AI-generated papers 100% of the time. However, the results should be taken with a grain of salt as the scope of the work was limited, and follow-up studies are needed to determine the extent of this approach's applicability.