Hi! I'm Sabrina, a final-year PhD candidate in Computer Science at George Mason University. My research sits at the intersection of NLP, large language models, and evaluation for high-stakes, expert-facing tasks in domains like educational assessment and AI policy.

I'm especially interested in the part of AI that often gets hand-waved: how we evaluate model quality when "accuracy" isn't enough. I build domain-specific benchmarking frameworks that measure reliability, bias, and how LLM outputs shape expert judgment in real workflows and use those signals to guide system iteration.

I'm advised by Prof. Antonis Anastasopoulos and I'm part of GMU's NLP Lab. I also have experience in speech recognition and machine translation.

Before my PhD, I earned a B.Sc. in Computer Science and Engineering from Bangladesh University of Professionals (2018). My undergraduate thesis focused on building a machine learning framework for sorting and classifying unstructured resume data.

Outside of research, I like reading and traveling. One bucket-list goal is visiting all 50 U.S. states — I've visited 20 states and 1 U.S. territory so far (and DC… does it count?). (Last updated: July 2025)

News

• Actively seeking full-time Applied AI / Research roles focused on LLM evaluation and NLP systems.
• BEA 2025: Paper on AI-enabled topic modeling in educational assessment accepted.
• EMNLP 2024 (Main): Paper on LLM influence in expert workflows accepted.
• NAACL 2024: Presented poster on multilingual news framing analysis.
• Received M.S. in Computer Science (GMU) and Distinguished Academic Achievement Award.
• Presented work on principal assessment at AEFP 2024 (Baltimore).
• Outstanding Graduate Teaching Assistant Award (2022–2023).