alt Hacker NewsHow would one prove the premise that a concept is not present in the training data?
With how much data is being shoveled in there, our default assumption should be that significant components are present.
How would one prove the premise that a concept is not present in the training data?
With how much data is being shoveled in there, our default assumption should be that significant components are present.
That would be a weird default assumption. It's not hard to come up with new ideas. In fact, it's trivial.
And if you want to know if a specific concept is known by the LLM, you can literally ask it. It generally does a great job of telling you what it is and is not familiar with.