A research study demonstrates that large language models can be persuaded to accept and defend false information when questioned, even when contradicted with accurate facts.

The Conversation

You can make AI chatbots spout information that's not true. Nicoletaionescu/iStock via Getty Images
When you ask a large language model a question, the reply may include falsehoods, and if you challenge those statements with facts, the AI may still uphold the reply as true. That’s what my research group found when we asked five leading models to describe scenes in movies or novels that don’t actually exist.
We probed this possibility after I asked ChatGPT its favorite scene in the movie “Good Wi