Who am I? 👀

Currently I am working at ETH Zurich and making language models better at multilinguality, in particular mid-resource/EEU languages. I completed my MSc in Statistics at ETH Zurich and BSc in Economic Cybernetics at National Technical University of Ukraine. I am actively involved in research around open-weight large language models, with a focus on multilinguality, safety and privacy.

In my free time I enjoy reading, playing volleyball and breaking LLMs😊

Here is the list of some papers which describe my research interests better than words can:

• Déjà Vu: Multilingual LLM Evaluation through the Lens of Machine Translation Evaluation
• Generative Data Refinement: Just Ask for Better Data
• Low-Resource Languages Jailbreak GPT-4
• Layer Swapping for Zero-Shot Cross-Lingual Transfer in Large Language Models
• Large Language Models are Advanced Anonymizers
• OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models
• The State of Multilingual LLM Safety Research: From Measuring the Language Gap to Mitigating It

I am also a long-time supporter of Zuerich hilft der Ukraine (ZhdU), check out their work!