LIMA demonstrated that instruction-tuning and output formatting could be trained with a limited number of samples, not that finetuning was incapable of adding new information to the model.
It may be sub-optimal in most cases to RAG, but it does work.
I've had trouble finding high quality sources of information about successful applications of fine-tuning to add knowledge to a model.
Anecdotally, I literally "added knowledge" to a model via fine-tuning earlier today.
Fine tuning can do extremely well given a specific question and answer, the tuned model "knows" how to answer that question much more accurately.
I gave it a specific question, and a good answer as a fine tuning input. (Literally 2 data points as the input, 2 questions/answer sets.)
I asked it that question, and the tuned model blows the base model away, for answering that specific question.
Validating on training data...What could possibly go wrong?
However: we were allowed to pick any base model in a given repo. All of the teams that “won” did so for the same reason: they had all picked the same base model (whereas a majority of teams picked the given default), presumably the one that had at some point been trained on the most favorable data for this particular challenge.
It was quite silly. Had everyone had the same base model we’d have a bit more of an interesting problem (more around NLP and alignment than picking the ‘best’ model).