| 2026 | ECIR | XProvence: Zero-Cost Multilingual Context Pruning for Retrieval-Augmented Generation. | Youssef Mohamed, Mohamed Elhoseiny, Thibault Formal, Nadezhda Chirkova |
| 2025 | ICLR | Provence: efficient and robust context pruning for retrieval-augmented generation. | Nadezhda Chirkova, Thibault Formal, Vassilina Nikoulina, Stphane Clinchant |
| 2024 | EMNLP | BERGEN: A Benchmarking Library for Retrieval-Augmented Generation. | David Rau, Herv Djean, Nadezhda Chirkova, Thibault Formal, Shuai Wang, Stphane Clinchant, Vassilina Nikoulina |
| 2024 | INLG | Zero-shot cross-lingual transfer in instruction tuning of large language models. | Nadezhda Chirkova, Vassilina Nikoulina |
| 2024 | NAACL | Key ingredients for effective zero-shot cross-lingual knowledge transfer in generative tasks. | Nadezhda Chirkova, Vassilina Nikoulina |
| 2023 | ACL | Should you marginalize over possible tokenizations? | Nadezhda Chirkova, Germn Kruszewski, Jos Rozen, Marc Dymetman |
| 2023 | ICLR | CodeBPE: Investigating Subtokenization Options for Large Language Model Pretraining on Source Code. | Nadezhda Chirkova, Sergey Troshin |
| 2021 | NAACL | On the Embeddings of Variables in Recurrent Neural Networks for Source Code. | Nadezhda Chirkova |
| 2021 | NAACL | A Simple Approach for Handling Out-of-Vocabulary Identifiers in Deep Learning for Source Code. | Nadezhda Chirkova, Sergey Troshin |
| 2020 | AAAI | Structured Sparsification of Gated Recurrent Neural Networks. | Ekaterina Lobacheva, Nadezhda Chirkova, Alexander Markovich, Dmitry P. Vetrov |
| 2018 | EMNLP | Bayesian Compression for Natural Language Processing. | Nadezhda Chirkova, Ekaterina Lobacheva, Dmitry P. Vetrov |