The Shape of Learning: Anisotropy and Intrinsic Dimensions in Transformer-Based Models

Anton Razzhigaev, Matvey Mikhalchuk, Elizaveta Goncharova, Ivan Oseledets, Denis Dimitrov, Andrey Kuznetsov

Main: Interpretability and Model Analysis in NLP Poster Paper

Session 4: Interpretability and Model Analysis in NLP (Poster)
Conference Room: Radisson
Conference Time: March 18, 16:00-17:30 (CET) (Europe/Malta)
TLDR:
You can open the #paper-194 channel in a separate window.
Abstract: