Ivan Vykopal

Ivan is a PhD student and member of the NLP team, specializing in machine learning, large language models, and multilingual natural language processing. He obtained his Master’s degree in Computer Science from the Faculty of Informatics and Information Technologies, where he focused on artificial intelligence and deep learning. During his studies, he participated in several research projects that applied deep learning and computer vision to medicine. His master’s thesis focused on medical image processing, specifically the segmentation of higher-level morphological structures to identify potential cardiac transplant rejection.

Currently, Ivan is a third-year PhD student, with expected graduation in 2026/2027. His research focuses on multilingual fact-checking, large language models, low-resource language processing, and Slovak NLP, with a particular emphasis on improving fact-checking systems across languages and resource conditions. He also completed a research visit at the German Research Center for Artificial Intelligence (DFKI), where he collaborated on multilingual NLP research.

His PhD research investigates how to build, transfer, and evaluate multilingual fact-checking systems in the era of large language models. His work covers the application of generative LLMs to fact-checking tasks in both monolingual and multilingual settings, including claim detection and previously fact-checked claim retrieval. A major part of his research addresses challenges in low-resource languages through cross-lingual transfer learning, parameter-efficient fine-tuning, and novel approaches for improving multilingual model performance. His research also focuses on evaluating source credibility, source attribution, and the groundedness of LLM-generated responses in fact-checking and chat assistant contexts.

Ivan has published at leading NLP venues, including ACL’24, EMNLP’25, NAACL’25, and EACL’26, with research on multilingual fact-checking, low-resource language transfer, and evaluation of LLMs in misinformation-related contexts. His work includes studies on soft language prompts for cross-lingual transfer, multilingual previously fact-checked claim detection, and evaluation of web search credibility and response groundedness in chat assistants.