Author

Irina Proskurina

Observed name: Proskurina, Irina

Institutions: Lyon 1 Université, Centre National de la Recherche Scientifique, Université Lumière Lyon 2, Laboratoire Hubert Curien

Observed institutions: Lyon 1 Université, Centre National de la Recherche Scientifique, Université Lumière Lyon 2, Laboratoire Hubert Curien

OpenAlex ID: A5153432500

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

2026 · Proskurina, Irina, Gourru, Antoine, et al. · arXiv (Cornell University)

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

2026 · Irina Proskurina, Guillaume Metzler, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)

Works count: 5

Citation count:

H-index:

I10-index: