We need a name for these pure hallucinations, something like lucies or looseys
Usually the hallucinations have some logic to them like a person with a similar spelling in some of the training sets. LLMs are mysterious!
Usually the hallucinations have some logic to them like a person with a similar spelling in some of the training sets. LLMs are mysterious!
I wonder how much of hallucinating/"mistakes" in LLMs is because the training data is full of us filling in additional info we humans commonly feel or interpret as implied rather than something which manifests from the architecture of the LLM itself. I assume only a small percentage, but also a non-zero one.