3 papers
cs.CL2026
When Do Concepts Become Functionally Sufficient During Language-Model Training?
Raphael Bernas, Paul G. Chevalier, Fanny Jourdan +1
Understanding a model and its learning mechanisms in depth requires identifying when its internal structures become useful, rather than simply looking at the final state. We study…
cs.CL2026
Revisiting Anisotropy in Language Transformers: The Geometry of Learning Dynamics
Raphael Bernas, Fanny Jourdan, Antonin Poché +1
Since their introduction, Transformer architectures have dominated Natural Language Processing (NLP). However, recent research has highlighted an inherent anisotropy phenomenon in…
cs.CL2025
Interpreto: An Explainability Library for Transformers
Antonin Poché, Thomas Mullor, Gabriele Sarti +8
Interpreto is an open-source Python library for interpreting HuggingFace language models, from early BERT variants to LLMs. It provides two complementary families of methods: attri…