Saved in:
Bibliographic Details
Main Authors: Li, Zeyu Michael, Vu, Hung Anh, Awofisayo, Damilola, Wenger, Emily
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.13899
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915516784836608
author Li, Zeyu Michael
Vu, Hung Anh
Awofisayo, Damilola
Wenger, Emily
author_facet Li, Zeyu Michael
Vu, Hung Anh
Awofisayo, Damilola
Wenger, Emily
contents Numerous works have noted similarities in how machine learning models represent the world, even across modalities. Although much effort has been devoted to uncovering properties and metrics on which these models align, surprisingly little work has explored causes of this similarity. To advance this line of inquiry, this work explores how two factors - dataset overlap and task overlap - influence downstream model similarity. We evaluate the effects of both factors through experiments across model sizes and modalities, from small classifiers to large language models. We find that both task and dataset overlap cause higher representational similarity and that combining them provides the strongest effect. Finally, we consider downstream consequences of representational similarity, demonstrating how greater similarity increases vulnerability to transferable adversarial and jailbreak attacks.
format Preprint
id arxiv_https___arxiv_org_abs_2505_13899
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Causes and Consequences of Representational Similarity in Machine Learning Models
Li, Zeyu Michael
Vu, Hung Anh
Awofisayo, Damilola
Wenger, Emily
Machine Learning
Numerous works have noted similarities in how machine learning models represent the world, even across modalities. Although much effort has been devoted to uncovering properties and metrics on which these models align, surprisingly little work has explored causes of this similarity. To advance this line of inquiry, this work explores how two factors - dataset overlap and task overlap - influence downstream model similarity. We evaluate the effects of both factors through experiments across model sizes and modalities, from small classifiers to large language models. We find that both task and dataset overlap cause higher representational similarity and that combining them provides the strongest effect. Finally, we consider downstream consequences of representational similarity, demonstrating how greater similarity increases vulnerability to transferable adversarial and jailbreak attacks.
title Causes and Consequences of Representational Similarity in Machine Learning Models
topic Machine Learning
url https://arxiv.org/abs/2505.13899