alt Hacker NewsI think you're missing the point. This is my own paper and these are my own new concepts. It doesn't matter if the definition of the new concepts are only 1% of the paper, the point is they are the concepts I'm asking the LLM to use, and are not in its training data.
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.