About

I’m Mahammed Kamruzzaman, a PhD student in the Bellini College of Artificial Intelligence, Cybersecurity and Computing at the University of South Florida (Tampa). I work under the supervision of Dr. Gene Louis Kim.

My research focuses on the safety and trustworthiness of generative AI systems, with particular emphasis on how large language models (LLMs) and vision-language models (VLMs) behave across diverse social and cultural domains. My work centers on building rigorous evaluation datasets and pipelines to analyze model behavior in high-stakes and subjective settings, including emotion attribution, toxicity and safety judgments, cultural norm interpretation, etc. Beyond measurement, I study bias mitigation strategies and investigate interpretability methods to understand why these biases emerge. I publish my research in top-tier NLP venues including ACL, EMNLP, AACL and their affiliated workshops.

I am fortunate to collaborate with researchers across academia and industry who work on responsible AI, fairness, and sociotechnical evaluations of foundation models. My collaborators include Dr. Gene Louis Kim (University of South Florida), Dr. Ninareh Mehrabi (Meta), Dr. Flor Miriam Plaza-del-Arco (Leiden University), Dr. Amanda Cercas Curry (CENTAI Institute), and Dr. Anshuman Chhabra (University of South Florida).

For more details, see my CV or reach out via email.