Evangelia Zve
Author directory2026
Measuring Embedding Sensitivity to Authorial Style in French: Comparing Literary Texts with Language Model Rewritings
Benjamin Icard | Lila Sainero | Alice Breton | Evangelia Zve | Jean-Gabriel Ganascia
Proceedings of the 6th International Conference on Natural Language Processing for the Digital Humanities
Benjamin Icard | Lila Sainero | Alice Breton | Evangelia Zve | Jean-Gabriel Ganascia
Proceedings of the 6th International Conference on Natural Language Processing for the Digital Humanities
Large language models (LLMs) can convincingly imitate human writing styles, yet it remains unclear how much stylistic information is encoded in embeddings from any language model and retained after LLM rewriting. We investigate these questions in French, using a controlled literary dataset to quantify the effect of stylistic variation via changes in embedding dispersion. We observe that embeddings reliably capture authorial stylistic features and that these signals persist after rewriting, while also exhibiting LLM-specific patterns. These analytical results offer promising directions for authorship imitation detection in the era of language models.
From Noise to Signal: When Outliers Seed New Topics
Evangelia Zve | Gauvain Bourgne | Benjamin Icard | Jean-Gabriel Ganascia
Proceedings of the Fifteenth Language Resources and Evaluation Conference
Evangelia Zve | Gauvain Bourgne | Benjamin Icard | Jean-Gabriel Ganascia
Proceedings of the Fifteenth Language Resources and Evaluation Conference
Outliers in dynamic topic modeling are typically treated as noise, yet we show that some can serve as early signals of emerging topics. We introduce a temporal taxonomy of news-document trajectories that defines how documents relate to topic formation over time. It distinguishes anticipatory outliers, which precede the topics they later join, from documents that either reinforce existing topics or remain isolated. By capturing these trajectories, the taxonomy links weak-signal detection with temporal topic modeling and clarifies how individual articles anticipate, initiate, or drift within evolving clusters. We implement it in a cumulative clustering setting using document embeddings from eleven state-of-the-art language models and evaluate it retrospectively on HydroNewsFr, a French news corpus on the hydrogen economy. Inter-model agreement reveals a small, high-consensus subset of anticipatory outliers, increasing confidence in these labels. Qualitative case studies further illustrate these trajectories through concrete topic developments.
Predicting Emerging Topics from Outliers: A Prospective Study of Weak Signals in Embedding Space
Evangelia Zve | Gauvain Bourgne | Jean-Gabriel Ganascia
Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026
Evangelia Zve | Gauvain Bourgne | Jean-Gabriel Ganascia
Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026
Some documents that embedding-based topic models initially classify as noise later become founding members of emerging topics. At publication time, however, they appear as scattered points in embedding space and are difficult to distinguish from ordinary noise without the benefit of hindsight. We study whether such *anticipatory outliers* can be predicted prospectively, using only information available when a document first appears. We derive labels from the subsequent trajectories of outlier documents, distinguishing those that anticipate new topics from those that reinforce existing topics or remain isolated, and estimate label confidence through agreement across multiple embedding models. On two French news corpora, anticipatory outliers prove predictable at publication time. Under cross-validation, F1 rises from about 0.77 over the full eligible population to above 0.90 on high-consensus subsets, and remains at 0.76–0.80 under a strictly chronological evaluation. Predictive performance is driven mainly by geometric features capturing each outlier’s position in embedding space.
2025
Représenter le style au-delà des thématiques : une étude d’impact sur la dispersion vectorielle de différents modèles de langage
Benjamin Icard | Evangelia Zve | Lila Sainero | Alice Breton | Jean-Gabriel Ganascia
Actes des 32ème Conférence sur le Traitement Automatique des Langues Naturelles (TALN), volume 2 : traductions d'articles publiés
Benjamin Icard | Evangelia Zve | Lila Sainero | Alice Breton | Jean-Gabriel Ganascia
Actes des 32ème Conférence sur le Traitement Automatique des Langues Naturelles (TALN), volume 2 : traductions d'articles publiés
Cet article vise à étudier comment le style d’écriture influence la dispersion des plongements vectoriels de divers grands modèles de langage. Alors que les premiers modèles de type transformeur étaient prin- cipalement axés sur la modélisation thématique, cette étude examine le rôle du style d’écriture dans la configuration de l’espace vectoriel. À partir d’un corpus littéraire faisant varier thématiques et styles, nous comparons la sensibilité des modèles de langage en français et en anglais. En analysant ainsi l’impact spécifique du style sur la dispersion vectorielle, nous cherchons à mieux comprendre com- ment les modèles de langage traitent l’information stylistique, contribuant ainsi à leur interprétabilité globale. Ceci est un résumé de l’article “Embedding Style Beyond Topics: Analyzing Dispersion Effects Across Different Language Models” publié dans les actes de la conférence COLING 2025 (Icard et al., 2025) et accessible à l’URL : https://aclanthology.org/2025.coling-main.236/.
From Outliers to Topics in Language Models: Anticipating Trends in News Corpora
Evangelia Zve | Benjamin Icard | Alice Breton | Lila Sainero | Gauvain Bourgne | Jean-Gabriel Ganascia
Proceedings of the 8th International Conference on Natural Language and Speech Processing (ICNLSP-2025)
Evangelia Zve | Benjamin Icard | Alice Breton | Lila Sainero | Gauvain Bourgne | Jean-Gabriel Ganascia
Proceedings of the 8th International Conference on Natural Language and Speech Processing (ICNLSP-2025)
Embedding Style Beyond Topics: Analyzing Dispersion Effects Across Different Language Models
Benjamin Icard | Evangelia Zve | Lila Sainero | Alice Breton | Jean-Gabriel Ganascia
Proceedings of the 31st International Conference on Computational Linguistics
Benjamin Icard | Evangelia Zve | Lila Sainero | Alice Breton | Jean-Gabriel Ganascia
Proceedings of the 31st International Conference on Computational Linguistics
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.
Search