Irina Proskurina

5 papers · 2022–2025 · 4 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (12) 🐣 Hot Topic Early Bird ❓ The Questioner (2)

Venues

NAACL (2) CoNLL (1) EACL (1) EMNLP (1)

Top co-authors

Julien Velcin (3) Guillaume Metzler (3) Irina Piontkovskaya (2) Ekaterina Artemova (2) Thibaud Leteno (1) Charlotte Laclau (1) Laida Kushnareva (1) Serguei Barannikov (1) Antoine Gourru (1) Evgeny Burnaev (1)

Research topics

Artificial Intelligence (4) Core AI (4) Deep Learning (2) Machine Learning (2) Natural Language Processing (2) Architectures (2) Interdisciplinary (1) Application Areas (1) Applications (1) Core Methods (1) Resources & Methods (1) Social (1) Techniques (1)

Keywords

large language model (2) topological data analysis (2) attention mechanism (1) confidence calibration (1) linguistic knowledge (1) language model (1) value alignment (1) human value (1) attention map (1) transformer language model (1) quantization loss (1) multilingual model (1) linguistic analysis (1) attention graph (1) moral reasoning (1) minimal pair (1) moral alignment (1) acceptability judgment (1) model compression (1) french dataset (1)

Papers

HISTOIRESMORALES: A French Dataset for Assessing Moral Alignment NAACL 2025 When Quantization Affects Confidence of Large Language Models? NAACL 2024 Can BERT eat RuCoLA? Topological Data Analysis to Explain EACL 2023 Mini Minds: Exploring Bebeshka and Zlata Baby Models CoNLL 2023 Acceptability Judgements via Examining the Topology of Attention Maps EMNLP 2022