[macleginn]

The presentation is nice! The main point, however, is a bit misleading. From the title, one would assume that we will see something about how LMs do all these things implicitly (as was famously shown for syntax in this paper: https://arxiv.org/pdf/2005.04511, for example), but instead the input is simply given to a bunch of pretrained task-specific models, which may not have much in common and definitely do not have very much in common with what today's LLMs are doing under the hood.

[toxik]

You shouldn’t link directly to the pdf, here is the abs page

https://arxiv.org/abs/2005.04511