Rheeya Uppaal

picture

I am a fourth year PhD student at the University of Wisconsin-Madison, where I work with Prof Junjie Hu on developing safe, truthful, and reliable language models that remain aligned with user-defined standards. My approach focuses on achieving these properties through interpretable interventions on model internals, enabling fine-grained control and transparency in behavior. ['23, '25] I am also interested in failure modes that emerge under distribution shift, including limits to generalization under limited supervision ['24, '23, '21] and hallucination in reasoning-focused vision-language models ['26]. Ultimately, my goal is to build transparent and trustworthy language systems whose safety, alignment, and generalization capabilities can be systematically understood and guided by design.

Prior to my PhD, I was a researcher at Goldman Sachs CoreAI, where I worked on information extraction and interpretability methods for text in the financial domain under Dr Vijay Saraswat. I completed my Masters in Computer Science at UMass Amherst, where I worked under the wonderful guidance of Prof Andrew McCallum and Prof Madalina Fiterau.

You can find my single page Resumé here, or a more detailed CV here.

What's New: