Irina Proskurina

Documents

Publications

	Towards an Ethical Compression of Large Language Models Irina Proskurina , Guillaume Metzler , Julien Velcin Journée Éthique et TAL 2024, Apr 2024, Nancy, France Conference papers hal-04646400v1
	When Quantization Affects Confidence of Large Language Models? Guillaume Metzler , Irina Proskurina , Julien Velcin , Luc Brun 2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Jun 2024, Mexico City, Mexico Conference papers hal-04646224v1
	The Other Side of Compression: Measuring Bias in Pruned Transformers Irina Proskurina , Guillaume Metzler , Julien Velcin IDA 2023 - 21th International Symposium on Intelligent Data Analysis, Apr 2023, Louvain-la-Neuve - Belgique, Belgium. pp.366-378, ⟨10.1007/978-3-031-30047-9_29⟩ Conference papers hal-04104840v1
	Acceptability Judgements via Examining the Topology of Attention Maps Daniil Cherniavskii , Eduard Tulchinskii , Vladislav Mikhailov , Irina Proskurina , Laida Kushnareva EMNLP 2022 Empirical Methods in Natural Language Processing, ACL Association for Computational Linguistics, Dec 2022, Abu-Dhabi, United Arab Emirates. pp.88-107, ⟨10.18653/v1/2022.findings-emnlp.7⟩ Conference papers hal-03995313v1

	Quand la quantification affecte-t-elle la confiance des grands modèles de langage ? Guillaume Metzler , Julien Velcin , Irina Proskurina , Luc Brun 2024 Preprints, Working Papers, ... hal-04646275v1