If you are using a model that links to its sources (like Microsoft Copilot, Perplexity, or Gemini), follow the links and read the original pages. Make sure the AI-generated summary aligns with the content of the page it came from. Also, ensure the page content is relevant to the task you asked the model to perform.
If you are using the free version of ChatGPT, which does not link to sources, it’s important to do a quick web search to verify the information. Look for more than one source to check the validity of what the AI is saying. Resources like Wikipedia or mainstream news sites that employ fact-checkers can be helpful.
Since the free version of ChatGPT doesn’t have an understanding of facts, it’s often better to use a model that links to its sources, like Perplexity or Microsoft Copilot, as this makes it easier to fact-check.
Additionally, because websites can also contain misinformation, try using the SIFT Method: Stop, Investigate the source, Find better coverage, and Trace claims to the original context.
Note: Free accounts on ChatGPT now have some access to web browsing, so it can look up more current information. However, there is a limit to the amount of web browsing available in one day. Once you reach that limit, you’ll automatically be switched back to the earlier version, which doesn’t include web browsing.
Adapted from "FAQs about generative AI" by Nicole Hennig, University of Arizona Libraries. Licensed under CC BY 4.0.
