Artificial intelligence chatbots have become ubiquitous study companions for students in medicine and dentistry, promising instant answers to virtually any exam question. But a new study from Hacettepe University in Türkiye suggests that getting the right answer is only half the story. When three leading large language models were put to the test on real periodontology exam questions, they performed remarkably similarly in terms of raw accuracy …
This story is only covered by news sources that have yet to be evaluated by the independent media monitoring agencies we use to assess the quality and reliability of news outlets on our platform. Learn more here.