7 papers
Formalizing the Moral Evaluation of Speech Acts: Truthfulness, Lies and Ethical Dilemmas
Benjamin Icard, Gauvain Bourgne, Jeanne Bonnaventure +1
In life-or-death situations, a benevolent lie may appear more moral than telling the truth. Yet such lies can backfire, producing unintended and sometimes fatal consequences. This…
Predicting Emerging Topics from Outliers: A Prospective Study of Weak Signals in Embedding Space
Evangelia Zve, Gauvain Bourgne, Jean-Gabriel Ganascia
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 scattere…
Propaganda Forensics: Recovering the Generation Pipeline of an AI-Driven Influence Campaign
Benjamin Icard, Elouan Vuichard, Louis Lefebvre +12
We present a forensic analysis of the generation pipeline behind a recent AI-driven influence campaign. We introduce PROPAGIA, a corpus of 2,646 propagandist French articles from t…
Measuring Embedding Sensitivity to Authorial Style in French: Comparing Literary Texts with Language Model Rewritings
Benjamin Icard, Lila Sainero, Alice Breton +2
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 a…
From Noise to Signal: When Outliers Seed New Topics
Evangelia Zve, Gauvain Bourgne, Benjamin Icard +1
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-doc…
From Outliers to Topics in Language Models: Anticipating Trends in News Corpora
Evangelia Zve, Benjamin Icard, Alice Breton +3
This paper examines how outliers, often dismissed as noise in topic modeling, can act as weak signals of emerging topics in dynamic news corpora. Using vector embeddings from state…
Embedding Style Beyond Topics: Analyzing Dispersion Effects Across Different Language Models
Benjamin Icard, Evangelia Zve, Lila Sainero +2
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 aligne…