Research Interest:
- Human-Computer Interaction: Developing intelligent decision support systems (IDSS) for effective human-AI collaboration. With a focus on disinformation detection and medical data analysis, we emphasize transparency, usability, and explainable AI (xAI) to ensure these systems are practical and trustworthy, incorporating transparency metrics throughout the design.
- Natural Language Processing: Specializing in Information Retrieval, Entity Recognition, Retrieval-Augmented Generation (RAG), and fine-tuning Large Language Models (LLMs) for a range of tasks, including detecting and countering disinformation narratives with high accuracy and contextual understanding.
- Legal and Ethical Considerations: Assessing the impact of regulations like the AI Act, DSA, GDPR, and the Data Act on AI-based systems. We investigate the challenges these frameworks present for data aggregation and the ethical development of IDSS in contexts like disinformation and sensitive data handling.