[jwjohnson314]

The interesting thing here to me is that the llm isn’t ‘hallucinating’, it’s simply regurgitating some data it digested during training.

[mvdtnz]

What's the difference?

[jwjohnson314]

I think of hallucinating as a phenomenon where the model makes up something that appears correct but isn’t. Citations to papers that don’t exist, for example. Regurgitating training data (which may or may not be correct) is a different issue.