English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Reliable application of machine learning is of primary importance to thepractical deployment of deep learning methods. A fundamental challenge is thatmodels are often unreliable due to overconfidence. In this paper, we estimate amodel's reliability by measuring \emph{the agreement between its latent space,and the latent space of a foundation model}. However, it is challenging tomeasure the agreement between two different latent spaces due to theirincoherence, \eg, arbitrary rotations and different dimensionality. To overcomethis incoherence issue, we design a \emph{neighborhood agreement measure}between latent spaces and find that this agreement is surprisinglywell-correlated with the reliability of a model's predictions. Further, we showthat fusing neighborhood agreement into a model's predictive confidence in apost-hoc way significantly improves its reliability. Theoretical analysis andextensive experiments on failure detection across various datasets verify theeffectiveness of our method on both in-distribution and out-of-distributionsettings.

Great Models Think Alike: Improving Model Reliability via Inter-Model Latent Agreement