← Search

Antonin Poché

2 accepted papers

2026

Revisiting Anisotropy in Language Transformers: The Geometry of Learning Dynamics

ICML 2026poster

Since their introduction, Transformer architectures have dominated Natural Language Processing (NLP). However, recent research has highlighted an inherent anisotropy phenomenon in these models, presenting a significant challenge to their geometric interpretation. Previous theoretical studies on this…

Cited by 2SourceScholar
2025

ConSim: Measuring Concept-Based Explanations’ Effectiveness with Automated Simulatability

ACL 2025long

Concept-based explanations work by mapping complex model computations to human-understandable concepts. Evaluating such explanations is very difficult, as it includes not only the quality of the induced space of possible concepts but also how effectively the chosen concepts are communicated to users…

Cited by 0SourcePDFScholar