Harmfulness analysis of Large Language Model answers to dental questions

It became common for patients to use the Internet as a source of solutions to medical questions, including dental problems. Furthermore, the use of Large Language Models has recently become widely available to the public. The aim of this study was to assess the safety of patients in the aspect of using Large Language Models to answer dental questions. Based on the experience of practicing dentists, a set of 30 questions was created. The models' responses were categorized by two independent dentists with 5 years of practice experience into categories evaluating safety and information reliability. It was shown that currently available models are not fully safe for dental patients. The frequent search for solutions to their dental problems and the lack of advanced medical knowledge among patients generate the need to create a safe place for patients on the web.