Saved in:
| Main Authors: | , , , |
|---|---|
| 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 |