Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2501.00828 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916547320086528 |
|---|---|
| author | Icard, Benjamin Zve, Evangelia Sainero, Lila Breton, Alice Ganascia, Jean-Gabriel |
| author_facet | Icard, Benjamin Zve, Evangelia Sainero, Lila Breton, Alice Ganascia, Jean-Gabriel |
| contents | This paper analyzes how writing style affects the dispersion of embedding vectors across multiple, state-of-the-art language models. While early transformer models primarily aligned with topic modeling, this study examines the role of writing style in shaping embedding spaces. Using a literary corpus that alternates between topics and styles, we compare the sensitivity of language models across French and English. By analyzing the particular impact of style on embedding dispersion, we aim to better understand how language models process stylistic information, contributing to their overall interpretability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_00828 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Embedding Style Beyond Topics: Analyzing Dispersion Effects Across Different Language Models Icard, Benjamin Zve, Evangelia Sainero, Lila Breton, Alice Ganascia, Jean-Gabriel Computation and Language Artificial Intelligence This paper analyzes how writing style affects the dispersion of embedding vectors across multiple, state-of-the-art language models. While early transformer models primarily aligned with topic modeling, this study examines the role of writing style in shaping embedding spaces. Using a literary corpus that alternates between topics and styles, we compare the sensitivity of language models across French and English. By analyzing the particular impact of style on embedding dispersion, we aim to better understand how language models process stylistic information, contributing to their overall interpretability. |
| title | Embedding Style Beyond Topics: Analyzing Dispersion Effects Across Different Language Models |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2501.00828 |