Fine-tuning even Lora on the open source models is nearly always better than these other approaches
Fine-tuning even Lora on the open source models is nearly always better than these other approaches
A model's weights are inherently lossy and opaque. If a model asserts some fact, it is impossible to tell whether that fact was true or hallucinated just from the model, because the model has no notion of "fact" or "truth", it's just probabilities.
Generating an answer solely from model weights is like asking a random person to answer a question from memory. Sure, you might get the right answer, but there's no guarantee.
Using RAG is like handing them a book and asking them what the book says the answer is. With the benefit that LLMs can "read" much faster than a human.
My take is that LLMs are actually much better at "reading" than they are at "writing", and RAG plays to that strength.
They are certainly much faster at reading than at writing. In fact, they re-read the entire context window for every token they write!
Fine-tuning is not a solution for getting fresh data as you would with RAG, unless you are planning to run your entire fine-tuning suite for every new document. It can help improve accuracy a bit when you need to specialise the model for a very specific domain or modality. In practice, this is rare and unnecessary for most use cases building on LLMs.
The counter argument to your assertion (my own opinion, not Microsoft's) is that the reason you hear so much about fine-tuning from everyone other than Open AI / MS, is that they offer less capable models that can't reliably produce the same quality of results without fine-tuning.
Can you expand on that? I've not seen evidence of that myself yet, but maybe I haven't looked in the right places.
"Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning" https://arxiv.org/abs/2205.05638