This paper describes a Natural Language Processing (NLP) course taught at Kyiv School of Economics. The course consists of 16 lectures, 5 practical assignments and focuses on modern large language models (LLMs) while preserving an introduction to classical NLP. Practical assignments are organized using Kaggle, where GPU support plays an important role in enabling students to work with complex models. A key feature of the course is the focus on Ukrainian in the practical assignments, contributing to the development of Ukrainian NLP expertise and community. The course is taught primarily in-person, but due to the ongoing war in Ukraine, also includes a full online participation option and additional weekly QnA sessions.

We participated in the Fourth UNLP shared task on detecting social media manipulation in Ukrainian Telegram posts, addressing both multilabel technique classification and token-level span identification. We propose two complementary solutions: for classification, we fine-tune the decoder-only model with class-balanced grid-search thresholding and ensembling. For span detection, we convert causal LLM into a bidirectional encoder via masked language modeling pretraining on large Ukrainian and Russian news corpora before fine-tuning. Our solutions achieve SOTA metric results on both shared task track. Our work demonstrates the efficacy of bidirectional pretraining for decoder-only LLMs and robust threshold optimization, contributing new methods for disinformation detection in low-resource languages.