Rheeya Uppaal

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 enabling effective generalization to new tasks and domains with limited or no supervision, emphasizing systematic generalization over data-driven memorization. ^{['24, '23, '21]} Ultimately, my goal is to build transparent and trustworthy language systems whose safety, alignment, and generalization capabilities can be 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:

• March 2025: I gave an invited talk at Cohere for AI’s Research Connections Community on developing robust Model Editing Techniques.
• Feb 2025: ProFS was accepted to ICLR 2025! Excited to have some great conversations in Singapore.
• Nov 2024: PhD Milestone check! I passed my qualifying exam and am now a PhD candidate!
• June 2024: Excited to start an internship at Amazon Science, where I'll be working under the guidance of Markus Dreyer and Mohit Bansal.