Miss Dominika Nadia Wojtczak

My research focuses on a multimodal machine learning approach to studying online misinformation, focusing on underexplored modalities (e.g., images and videos, behavioural cues). After examining these modalities and text-based content, I began evaluating the cognitive abilities of large language models (LLMs) in detecting and interpreting misinformation. My work compares LLM performance with human annotators on tasks requiring complex judgment. I also investigate how different prompt-engineering strategies affect model performance and address ethical considerations in deploying LLMs for content moderation.