Personalizing AI Models with Kelvin Guu, Senior Staff Research Scientist, Google Brain

**Kelvin Guu** (0:05)
I'm very interested in recipes that allow people to adapt things easily. It's not yet clear what the right interface is. If someday, for example, people had their own in-home language model, which of course doesn't exist right now, you might even say like, oh, these are our family values, we want the language model to have those values. Would that be through just writing down your kind of family values on an instruction prompt and just saying, please follow these everywhere? Or is it going to be through repeated feedback where you talk to the language model and you say, no, I don't think you should say that.
It is not clear to me how that will go.

**Sarah Guo** (0:38)
Do as I say, not as I do seems easier, in this case. Thanks.
This is the No Priors podcast. I'm Sarah Guo. We invest in, advise, and help start technology companies.

**Elad Gil** (0:54)
In this podcast, we're talking with the leading founders and researchers in AI about the biggest questions.

**Sarah Guo** (1:06)
You. How do you personalize AI models? A popular school of thought in AI is just to dump all the data you need into pre-training or fine-tuning. But that's costly and less controllable than using AI models as a reasoning engine against an external data source.
And thus, the intersection of retrieval with LMS has become an increasingly interesting topic.
Today, we're going to talk to Kelvin Guu, Senior Staff Research Scientist at Google, who wants to make machine learning cheaper, accessible and easier.
He's joining us to talk about the newest methods his team is working on in AI training and language understanding. Kelvin, welcome to No Priors.

**Kelvin Guu** (1:37)
Hey, thanks for having me.

**Sarah Guo** (1:38)
Let's do a little bit of background. You started out studying math, but pivoted to natural language. What encouraged that switch?

**Kelvin Guu** (1:44)
Yeah, I actually had always wanted to get into tools that would help people learn more easily and find information more quickly.
My motivation for going into the math was really to build a good foundation for getting into many of those deeper questions. And I would say that also motivated my venturing into statistics. So my PhD was actually in the statistics department, but I quickly then migrated over to the NLP group at Stanford where I just learned a lot and had a great time.

**Sarah Guo** (2:10)
You chose to go to Google after your PhD. You've been there since 2018 Like, how has your focus or work changed during that time?

**Kelvin Guu** (2:18)
Yeah, I would say at Google, this was really just the dream place for me to deepen my focus on building tools that help people find information better.
And at the time that I joined, it was also just an extremely productive period where lots of new ideas were coming out. The group that I'm part of right now, which is now part of Google Brain, at the time was looking into very, at the time, early ideas on pre-training language models, which eventually became BERT. And that work just opened up a lot of frontiers for me, both in terms of product work at Google and inspiring new research ideas. I think one of the things that became very apparent early on when playing with BERT was, unlike all the prior generations of models, it had a large amount of world knowledge that we didn't deliberately encode into it. It wasn't in, you know, the fine-tuning data. It was all within pre-training.
And that has just many, I think, very obvious use cases now. But that also inspired me to, and my colleagues, to start thinking about retrieval-augmented models and getting even more knowledge into them. And I'm sure we'll be talking about that more here.

**Sarah Guo** (3:24)
Yeah, let's do that. Let's talk about Realm, which, our listeners, was a really landmark paper in the field.
In the paper and your talks about your model, you described the limitation of AI in domain knowledge or specialized knowledge that can be retrieved and represented more accurately. What motivated the paper?

**Kelvin Guu** (3:39)
Sure, yeah. So there are a few different things that can bring people to this retrieval-augmented modeling literature. One of them was kind of our original goal, which was to increase the memorization capacity of these models.
A second goal that you might come to this from is for modularity. So you might imagine that you have different data sources and you'd like to be able to swap one in or take one out the same way you could do with a database. There are just so many business applications where that's helpful. A third is anytime you're dealing with a very timely application, so there's new information arriving daily about, say, a sports team or any other type of event, you really want to be able to incorporate that quickly without retraining. So these are some of the common ways that people arrive in the space, and it's a very natural thing, I think, now to think about, well, I don't want to retrain, and yet I've got all this information out there, and it's human interpretable, it's text.