Communication Dans Un Congrès Année : 2025

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

Résumé

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.

Fichier principal
Vignette du fichier
2501.00828v1.pdf (1.52 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-04862898 , version 1 (03-01-2025)

Licence

Identifiants

Citer

Benjamin Icard, Evangelia Zve, Lila Sainero, Alice Breton, Jean-Gabriel Ganascia. Embedding Style Beyond Topics: Analyzing Dispersion Effects Across Different Language Models. 31st International Conference on Computational Linguistics (COLING), Jan 2025, Abu Dhabi, United Arab Emirates. ⟨hal-04862898⟩
226 Consultations
203 Téléchargements

Altmetric

Partager

  • More