Laboratoire Hubert Curien

AI & ML interests

None defined yet.

Recent Activity

iproskurina  updated a Space 8 days ago

LabHC/dike-leaderboard

iproskurina  authored a paper 26 days ago

The Fairness Collapse Phenomenon: Bias Amplification in Language Models Trained on Synthetic Data

iproskurina  authored a paper 26 days ago

Debias-SparseGPT: Bias-Aware Pruning for Large Language Models

View all activity

Papers

Histoires Morales: A French Dataset for Assessing Moral Alignment

View all Papers

Team members 7