91 citations · 100 across the 5 of their papers we have counts for
5 papers
GRANITE: A Generalized Regional Framework for Identifying Agreement in Feature-Based Explanations
Julia Herbinger, Gabriel Laberge, Maximilian Muschalik +3
Feature-based explanation methods aim to quantify how features influence the model's behavior, either locally or globally, but different methods often disagree, producing conflicti…
Efficiency vs. Alignment: Investigating Safety and Fairness Risks in Parameter-Efficient Fine-Tuning of LLMs
Mina Taraghi, Yann Pequignot, Amin Nikanjam +2
Organizations increasingly adapt Large Language Models (LLMs) from public repositories such as HuggingFace to downstream tasks. Prior work shows that even fine-tuning on benign dat…
Understanding Interventional TreeSHAP : How and Why it Works
Gabriel Laberge, Yann Pequignot
Shapley values are ubiquitous in interpretable Machine Learning due to their strong theoretical background and efficient implementation in the SHAP library. Computing these values…
Partial Order in Chaos: Consensus on Feature Attributions in the Rashomon Set
Gabriel Laberge, Yann Pequignot, Alexandre Mathieu +2
Post-hoc global/local feature attribution methods are progressively being employed to understand the decisions of complex machine learning models. Yet, because of limited amounts o…
How to Certify Machine Learning Based Safety-critical Systems? A Systematic Literature Review
Florian Tambon, Gabriel Laberge, Le An +7
Context: Machine Learning (ML) has been at the heart of many innovations over the past years. However, including it in so-called 'safety-critical' systems such as automotive or aer…