I am a PhD student under the supervision of Prof. Rico Sennrich. My research is a part of the NCCR Evolving Language , where I will be specializing in the knowledge representations of the multilingual LLMs.

• Subword tokenization, especially robustness towards noise, multilingual tokenizers, and token-free models
  • robust to noise tokenization preprocessing Czech-Ukrainian MT at TokShop@ICML2025: text, video, Github repo
• Factual knowledge in LLMs, especially its multilingual alignment and mechanistic interpretability
  • how much we lose with ungrammatical prompts - analysis of multilingual factual benchmarks at EMNLP2025: text, video, Github repo
• MT metrics, especially terminology in MT
  • term consistency metric at WMT2022: text
  • terminology shared task at WMT2023 - organizer: text
  • terminology shared task at WMT 2025 - organizer:  text, Github repo
• Corpus linguistics and language data resources:
  • manager of the Russian-Chinese parallel corpus (2018-2021)
  • contributed to data collection of the Russian dialect corpus (Ustja River Basin, 2017)
  • contributed to data collection and annotation of the Russian learner corpus (2017-2018)

Google Scholar page

University of Zurich:

Other Universities: 

• Teaching "General Morphology" course at the Faculty of Liberal Arts and Sciences, Montenegro

• "Do we need linguists for IT in the ChatGPT era?". At Auditoria Budva, 17 August 2025. video [in Russian]
• Talk with Boris Orekhov about Charles University. Ayva League podcast, 9 July 2024. audio [in Russian]
• Russian-Chinese Parallel Corpus. Laowaicast, 12 January 2021. audio, podcast page [in Russian]