Hi, I’m Nityaa, an AI researcher working in natural language processing (NLP) with a strong focus on explainable, responsible, and ethical AI.

I am interested in building and evaluating systems that make model behavior transparent, interpretable, and easier to audit, especially in high-stakes or socially sensitive settings.

I am currently at Tilburg University, where I work on designing small language models and LLM fairness. My master thesis was about thematic bias in book recommender systems. Feel free to check it out here.

More broadly, my interests include:

  • Ethical and responsible AI practices across the ML lifecycle
  • Explainability and interpretability for NLP models
  • Understanding and mitigating bias in data and models
  • The human side of AI work, including how models are used and understood in practice

I occasionally write about research workflows, projects I build, and lessons learned from applied ML research. If you would like to collaborate or chat, feel free to reach out!