3 papers
cs.LG2025
Can Linear Probes Measure LLM Uncertainty?
Ramzi Dakhmouche, Adrien Letellier, Hossein Gorji
Effective Uncertainty Quantification (UQ) represents a key aspect for reliable deployment of Large Language Models (LLMs) in automated decision-making and beyond. Yet, for LLM gene…
cs.LG2025
Why Cannot Neural Networks Master Extrapolation? Insights from Physical Laws
Ramzi Dakhmouche, Hossein Gorji
Motivated by the remarkable success of Foundation Models (FMs) in language modeling, there has been growing interest in developing FMs for time series prediction, given the transfo…
cs.LG2025
Machine Unlearning Meets Adversarial Robustness via Constrained Interventions on LLMs
Fatmazohra Rezkellah, Ramzi Dakhmouche
With the increasing adoption of Large Language Models (LLMs), more customization is needed to ensure privacy-preserving and safe generation. We address this objective from two crit…