COLING 2025main0 citations

Embedding Style Beyond Topics: Analyzing Dispersion Effects Across Different Language Models

Benjamin Icard, Evangelia Zve, Lila Sainero, Alice Breton, Jean-Gabriel Ganascia

Abstract

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.

BibTeX
@inproceedings{icard-etal-2025-embedding,
    title = "Embedding Style Beyond Topics: Analyzing Dispersion Effects Across Different Language Models",
    author = "Icard, Benjamin  and
      Zve, Evangelia  and
      Sainero, Lila  and
      Breton, Alice  and
      Ganascia, Jean-Gabriel",
    editor = "Rambow, Owen  and
      Wanner, Leo  and
      Apidianaki, Marianna  and
      Al-Khalifa, Hend  and
      Eugenio, Barbara Di  and
      Schockaert, Steven",
    booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
    month = jan,
    year = "2025",
    address = "Abu Dhabi, UAE",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.coling-main.236/",
    pages = "3511--3522"
}
Embedding Style Beyond Topics: Analyzing Dispersion Effects Across Different Language Models · COLING 2025