You can persuade AI models to accept falsehoods as truth, study shows

Large language models can uphold falsehoods they or human users state, despite being presented with evidence to the contrary.

By: Ashique KhudaBukhsh, Rochester Institute of Technology, The Conversation

Outlets: The Conversation

Published: May 31, 2026

Words: 806

Last Updated: 1 month, 3 weeks ago

Body Text Preview

By Ashique KhudaBukhsh, Rochester Institute of Technology

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 …

Create a free account to access this story and more

Join Plucky Wire to access full stories, collaborate with newsrooms, and discover content from networks around the world.

About

FAQ

Email Us