Publications | Francis Kulumba

Francis Kulumba, Guillaume Vimont, Laurent Romary, Florian Cafiero. Where Does Authorship Signal Emerge in Encoder-Based Language Models?. ArXiv, 2026.

Théo Lasnier, Wissam Antoun, Francis Kulumba, Djamé Seddah. Triggers Hijack Language Circuits: A Mechanistic Analysis of Backdoor Behaviors in Large Language Models. ArXiv, 2026.

Francis Kulumba, Wissam Antoun, Théo Lasnier, Djamé Seddah, Benoît Sagot. Language-Switching Triggers Take a Latent Detour Through Language Models. ArXiv, 2026.

Wissam Antoun, Francis Kulumba, Rian Touchent, Éric de la Clergerie, Benoît Sagot, Djamé Seddah. CamemBERT 2.0: A Smarter French Language Model Aged to Perfection. ArXiv, 2024.

Francis Kulumba, Wissam Antoun, Guillaume Vimont, Laurent Romary, Florian Cafiero. HALvest-Contrastive: Retrieval-Like Authorship Attribution with Patch-Level Late Interaction. ArXiv, 2024.