Peter Bloem on Nostr: The "statistically probable" part refers to the pre-trained model, not the fine-tuned ...

The "statistically probable" part refers to the pre-trained model, not the fine-tuned one.

One example is asking "when's my birthday". The pre-trained model doesn't know, and so picks a random answer from all possible dates. That's hallucination.

The finetuned model takes that uncertainty, but expresses it as the answer "I don't know".

Sometimes the finetuning fails and we get hallucination in chatbots. This is because they are overtrained to be certain.