AI Research

UF researchers evaluate academic performance of chatbots

In a new study, UF researchers found OpenAI’s GPT-4 performed better than the student average on seven of nine graduate-level exams in the biomedical sciences. But they found its performance on the free-text assessments was limited for some types of complex questions, raising concerns about irrelevant data and plagiarism.

Digital chatbot and notifications message alert screen icon and sent to recipient on laptop, Artificial intelligence, innovation and technology.