Do Transformers Use their Depth Adaptively? Evidence from a Relational Reasoning Task

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Curth, Alicia, Lawrence, Rachel, Karmalkar, Sushrut, Prasad, Niranjani
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!