T Lasnier

Home Publications Resume

All Articles

Disentangling meaning from language in LLM based MT

Théo Lasnier $^*$ , Armel Randy $^*$ , Djamé Seddah, Rachel Bawden, Benoît Sagot (2026)

Under reviewMachine TranslationMechanistic InterpretabilityArXiv Code

When Tables Go Crazy: Evaluating Multimodal Models on French Financial Documents

Virginie Mouilleron, Théo Lasnier, Djamé Seddah (2026)

Under reviewBenchmarkFinanceArXiv

Triggers Hijack Language Circuits: A Mechanistic Analysis of Backdoor Behaviors in Large Language Models

Théo Lasnier, Wissam Antoun, Francis Kulumba, Djamé Seddah (2026)

Under reviewLLM SafetyMechanistic InterpretabilityArXiv