Skip to content

About limitations on the task #2

@WuTianming

Description

@WuTianming

Hi, and thank you for your great work!

I was wondering if the early exit techniques introduced in the paper can be extended to be used with language modeling, or do they only apply to classification tasks? I think the only difference is that (1) language modeling has a rather large answer space at tens of thousands of vocabularies, and that (2) language models usually output a probability distribution to be sampled. Maybe it is because the conservative predictions are not strong enough when facing such a large number of possible sampling outcomes?

I see that you have a later work (CALM) addressing the case on language models by enforcing the early-exit objective during training, but I think the approaches used in CATs are more desirable because it is distribution-free and model-agnostic.

Thank you for your time!

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions