A curated collection of datasets in French, designed to evaluate biases in LLMs
Irina Proskurina PRO
iproskurina
AI & ML interests
LLMs: quantization, pre-training
Recent Activity
upvoted a paper about 6 hours ago
The Fairness Collapse Phenomenon: Bias Amplification in Language Models Trained on Synthetic Data authored a paper 2 days ago
The Fairness Collapse Phenomenon: Bias Amplification in Language Models Trained on Synthetic Data authored a paper 2 days ago
Debias-SparseGPT: Bias-Aware Pruning for Large Language Models