> Type safety is not factual correctness.

I very much agree with this and want to hone in on where do actually disagree. Would you say a linear classifier hallucinates?

Hallucinations were defined in the context of text generation models so your question does not really make sense.

IMO your system can make mistakes that are similar in spirit to hallucination (i.e. answering with a false answer instead of abstaining to answer).

Let's say classifiers don't hallucinate. To make a fair comparison we should constrain LLMs to the same classification task. In that case, no, LLMs also don't hallucinate.

- Give Jev and LLM the same input

- Lock down both to approved/rejected/unknown (LLM restricts on decoding)

- Both can be wrong, but neither can hallucinate (invent an another option).