Saved in:
Bibliographic Details
Main Authors: Cheng, Emily, Doimo, Diego, Kervadec, Corentin, Macocco, Iuri, Yu, Jade, Laio, Alessandro, Baroni, Marco
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2405.15471
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909597215752192
author Cheng, Emily
Doimo, Diego
Kervadec, Corentin
Macocco, Iuri
Yu, Jade
Laio, Alessandro
Baroni, Marco
author_facet Cheng, Emily
Doimo, Diego
Kervadec, Corentin
Macocco, Iuri
Yu, Jade
Laio, Alessandro
Baroni, Marco
contents A language model (LM) is a mapping from a linguistic context to an output token. However, much remains to be known about this mapping, including how its geometric properties relate to its function. We take a high-level geometric approach to its analysis, observing, across five pre-trained transformer-based LMs and three input datasets, a distinct phase characterized by high intrinsic dimensionality. During this phase, representations (1) correspond to the first full linguistic abstraction of the input; (2) are the first to viably transfer to downstream tasks; (3) predict each other across different LMs. Moreover, we find that an earlier onset of the phase strongly predicts better language modelling performance. In short, our results suggest that a central high-dimensionality phase underlies core linguistic processing in many common LM architectures.
format Preprint
id arxiv_https___arxiv_org_abs_2405_15471
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Emergence of a High-Dimensional Abstraction Phase in Language Transformers
Cheng, Emily
Doimo, Diego
Kervadec, Corentin
Macocco, Iuri
Yu, Jade
Laio, Alessandro
Baroni, Marco
Computation and Language
A language model (LM) is a mapping from a linguistic context to an output token. However, much remains to be known about this mapping, including how its geometric properties relate to its function. We take a high-level geometric approach to its analysis, observing, across five pre-trained transformer-based LMs and three input datasets, a distinct phase characterized by high intrinsic dimensionality. During this phase, representations (1) correspond to the first full linguistic abstraction of the input; (2) are the first to viably transfer to downstream tasks; (3) predict each other across different LMs. Moreover, we find that an earlier onset of the phase strongly predicts better language modelling performance. In short, our results suggest that a central high-dimensionality phase underlies core linguistic processing in many common LM architectures.
title Emergence of a High-Dimensional Abstraction Phase in Language Transformers
topic Computation and Language
url https://arxiv.org/abs/2405.15471