Kristína Okasová

Kristína holds both a Bachelor’s degree in Informatics and a Master’s degree in Intelligent Software Systems from the Slovak University of Technology. Her interest in artificial intelligence began early in her studies, with a focus on machine learning for her Bachelor’s thesis — work that later led to a published article and first sparked her consideration of a research career. Over time, her curiosity developed into a strong focus on deep learning and natural language processing, and for her Master’s thesis, she explored fine-tuning large language models. Before starting her PhD, she also gained experience in the IT industry, working for two years as an ABAP developer. She has since developed a passion for exploring the many open questions surrounding LLMs, from advancing their reasoning abilities and mitigating hallucinations to making them more accessible for speakers of underrepresented languages such as Slovak. She is eager to see which direction her PhD journey will take and is excited by the opportunity to deepen her expertise as the field continues to evolve.

Supervising team: Michal Gregor (KInIT)

Large language models (LLMs) are a powerful tool driving recent progress in artificial intelligence (AI). They integrate broad world knowledge into AI systems, follow natural language instructions, perform tasks in few-shot settings thanks to in-context learning, and increasingly support multiple modalities such as images and audio.
Despite these advances, LLMs face limitations that hinder their safe and widespread use. They tend to produce unsupported outputs (hallucinations), struggle with multi-step reasoning and planning, and show weaknesses in multimodal integration, such as recognizing fine-grained visual concepts. Moreover, they acquire new knowledge and skills with far lower sample efficiency than humans, which poses particular challenges for low-resource languages.