Scholar
Fanny Jourdan
Google Scholar ID: ntU8A30AAAAJ
Researcher at IRT Saint Exupéry
Natural Language Processing
Explainability
Fairness
Interpretability
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
62
H-index
4
i10-index
3
Publications
9
Co-authors
8
list available
Publications
8 items
Neuralyzing the Trace: Selective Representation-Level Unlearning with Contrastive Sparse Autoencoders
2026
Cited
0
Limitations of Automated Simulatability: LLM Simulators Can Bypass Explanations
2026
Cited
0
When Do Concepts Become Functionally Sufficient During Language-Model Training?
2026
Cited
0
Revisiting Anisotropy in Language Transformers: The Geometry of Learning Dynamics
2026
Cited
0
Interpreto: An Explainability Library for Transformers
2025
Cited
0
FairTranslate: An English-French Dataset for Gender Bias Evaluation in Machine Translation by Overcoming Gender Binarity
2025
Cited
0
EuroBERT: Scaling Multilingual Encoders for European Languages
2025
Cited
0
ConSim: Measuring Concept-Based Explanations' Effectiveness with Automated Simulatability
2025
Cited
0
Co-authors
8 total
Laurent Risser
CNRS - Toulouse Mathematics Institute - ANITI
Nicholas Asher
CNRS Research Director (DRCE), member ANITI
Agustin Martin Picard
ML Research Engineer, IRT Saint-Exupéry
Thomas Fel
Kempner Fellow, Harvard University
Nicolas Boizard
PhD Studdent @University of Paris-Saclay (MICS - CentraleSupelec) x Diabolocom
Louis Béthune
Apple Machine Learning Research
Alon Jacovi
Google Research
Antonin Poché
Research engineer at IRT Saint Exupery
