About me
I am a second year Ph.D. student in the Allen School of Computer Science and Engineering at the University of Washington, advised by Yulia Tsvetkov. I do research in Natural Language Processing, and I'm particularly interested in using computational methods to model and potentially discover cognitive processes.
Before grad school, I received my B.S. and M.S.E. at Johns Hopkins with majors in Computer Science, Cognitive Science (linguistics focus), and Applied Mathematics (statistics focus). I worked as a research assistant at the Center for Language and Speech Processing advised by Philipp Koehn and Kenton Murray.
My research interests: NLP, Clinical Reasoning, Social Reasoning, Human-Centered NLP, Multilinguality, and more!
Please contact me at stelli [at] cs.washington.edu if you are interested in my work!
Click here to view my CV (updated Dec. 24)
Current Projects
-
Proactive Reasoning
I'm thinking about how to identify and proactively seek information using LLMs to improve model safety & reliability with statistical guarantee. How to make LLMs ask good questions? How do we model "intuition" in expert domains?
-
Socially-Intelligent Personalization
How do people in different social groups interact differently? How do unspoken rules shape behaviors and interactions? We need to first learn these explicit & implicit social preferences of users, then personalize models to interact accordingly.
News
-
2025-02
Check out our new paper "ALFA: Aligning LLMs to Ask Good Questions A Case Study in Clinical Reasoning by decomposing a complex goal into attributes and synthesizing paired data for preference learning.
-
2024-12
Presenting MediQ at Neurips2024 in Vancouver 🍁.
-
2024-11
Presenting ValueScope and Multilingual Abstention at EMNLP2024 in Miami 🌴.
-
2024-09
Joining Meta FAIR as a visiting researcher.
-
2024-08
Giving a talk at Responsible AI for Health Symposium (RAIHS) on MediQ.
-
2024-08
Giving a talk at MSR Real-world Evidence Lab on MediQ.
-
2024-07
Check out our new paper "ValueScope: Unveiling Implicit Norms and Values via Return Potential Model of Social Interactions to see how we "read the room" using LLMs.
-
2024-06
Check out our new paper "MEDIQ: Question-Asking LLMs for Adaptive and Reliable Clinical Reasoning in which we teach LLMs to ask--instead of answer--clinical questions!
-
2023-12
Presenting Condensing Multilingual Knowledge with Lightweight Language-Specific Modules at EMNLP2023 in Singapore!
