Oly Sourbut

There are already kind of examples of that.

So you may have heard of retrieval augmented generation, RAG.

This is a kind of very common way of kind of scaffolding up an LM is you provide a corpus of extra materials.

Maybe it's like some materials on a particular domain.

Those are indexed sort of semantically.

And then the model, rather than doing a web search, you can do a kind of search into this index and retrieve content and then

that content enters the model context, and then the subsequent answer or generation or whatever it is can incorporate that.

And there are already evaluations that people build for how grounded are the generations of systems which are using these retrieval-augmented components.

And so I can imagine that's a microcosm of this epistemic virtue of being thorough or something like that.

And so you can imagine really expanding the way that people are looking at this.

And a big part of that is things like being biased or being particularly sensitive to framing or treating particular

people or characters or institutions, preferentially or dis-preferentially, these kind of virtues, again, you can kind of produce evaluations that at least give some confidence.

I'm not going to use the word guarantee again, but at least produce some confidence that the systems, when deployed in other important contexts, are not going to have these kind of pernicious properties.

Another thing is, again, thinking about RAG, retrieval augmented generation,

And thinking about web search as a kind of augmentation there.

And the importance of legibility of the inputs which have been gathered for a given downstream generation or task or whatever.

I think that's an important thing as well, that kind of auditability and traceability.

And then knowing that the corpora being drawn from, so whether it's the web search indexes or whether it's these kind of RAG indexes, knowing that those are themselves well-constructed, well-structured, and are able to provide these auditability, legibility guarantees.

that can also enable these systems.

So then it's not about the element itself.