The number of large language models (LLMs) has ballooned with ChatGPT garnering particular attention. They have made, and are expected to continue making, vast improvements to the organization and reporting of information. However, the output of LLMs can contain novel and inaccurate content—in other words misinformation. Reports that are unsuccessfully scraped of misinformation can lead to erroneous decision making. Such a situation far from desirable.

