1 citations · 1 across the 8 of their papers we have counts for
9 papers
Neuralyzing the Trace: Selective Representation-Level Unlearning with Contrastive Sparse Autoencoders
Itai Zehavi, Fanny Jourdan, Ulrich Aivodji
Machine unlearning aims to remove targeted information while preserving a model's other abilities. In realistic settings, such as privacy requests under the EU GDPR, the target may…
Limitations of Automated Simulatability: LLM Simulators Can Bypass Explanations
Antonin Poché, Fanny Jourdan, Nils Feldhus +6
Simulatability is an evaluation protocol for explanations that quantifies their usefulness by how well they help a user predict a task model's outputs. Since human evaluation is co…
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…
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…
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…
FairTranslate: An English-French Dataset for Gender Bias Evaluation in Machine Translation by Overcoming Gender Binarity
Fanny Jourdan, Yannick Chevalier, Cécile Favre
Large Language Models (LLMs) are increasingly leveraged for translation tasks but often fall short when translating inclusive language -- such as texts containing the singular 'the…
EuroBERT: Scaling Multilingual Encoders for European Languages
Nicolas Boizard, Hippolyte Gisserot-Boukhlef, Duarte M. Alves +16
General-purpose multilingual vector representations, used in retrieval, regression and classification, are traditionally obtained from bidirectional encoder models. Despite their w…
ConSim: Measuring Concept-Based Explanations' Effectiveness with Automated Simulatability
Antonin Poché, Alon Jacovi, Agustin Martin Picard +2
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…
Advancing Fairness in Natural Language Processing: From Traditional Methods to Explainability
Fanny Jourdan
The burgeoning field of Natural Language Processing (NLP) stands at a critical juncture where the integration of fairness within its frameworks has become an imperative. This PhD t…