Comment by great_psy
3 days ago
Maybe I’m not creative enough to see the potential, but what value does this bring ?
Given the example I saw about CRISPR, what does this model give over a different, non explaining model in the output ? Does it really make me more confident in the output if I know the data came from Arxiv or Wikipedia ?
I find the LLM outputs are subtlety wrong not obviously wrong
It makes the black box slightly more transparent. Knowing more in this regard allows us to be more precise—you go from prompt tweak witchcraft and divination to more of possible science and precise method.
Can this method be extended to go down to the sentence level ?
In the example it shows how much of the reason for an answer is due to data from Wikipedia. Can it drill down to show paragraph or sentence level that influences the answer ?
Your question should be "Can it drill down to show the paragraphs or sentences that influence the answer?"
I believe that the plagiarism complaint about llm models comes from the assumption that there is a one-to-one relationship between training and answers. I think the real and delightfully messier situation is that there is a many-to-one relationship.
3 replies →
Great questions. We have several posts in the works that will drill down more into these things. The model was actually designed to answer these questions for any sentence (or group of tokens it generates).
It can tell you which specific text (chunk) in the training data that led to the output the model generated. We plan to show more concrete demos of this capability over the coming weeks.
It can tell you where in the model's representation it learned about science, art, religion etc. And you can trace all of these to either to input context, training data, or model's representations.
Does it? If i make a system prompt for most models right now, tell them they were trained on {list} of datasets, and to attribute their answer to their training data, i get quite similar output. It even seems quite reasonable. The reason being each data corpus has a "vibe" to it and the predictions simply assign response vibe to dataset vibe.
That's still firmly in divination land.