Rheeya Uppaal

I am a third year PhD student at the University of Wisconsin-Madison, where I work with Prof Junjie Hu on building reliable language models that are truthful ^['23] and aligned to user defined standards, by intervening on a model's internal architecture ^['24]. I am also interested in developing techniques for language models to generalize to tasks and domains with limited or no supervision. ^{['24, '23, '21, '19]}

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.