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: Natural Language Processing, Multilingual NLP, Clinical Reasoning, Social Reasoning, Human-Centered NLP
Please contact me at stelli [at] cs.washington.edu if you are interested in my work!
Click here to view my CV (updated Sep. 23)
Current Projects
-
Interactive Medical Reasoning
I'm thinking about how to identify and proactively seek information using LLMs to improve diagnostic accuracy with statistical guarantee. How to make LLMs ask good questions? How do we model "intuition" in expert domains?
-
Community Norms & Values
How do people in different social groups interact differently? How do unspoken rules shape behaviors and interactions? This project aims to surface linguistic and social norms in online communities and reflect the discovered norms in LLM agents.
News
-
11/14/2024
Presenting ValueScope and Multilingual Abstention at EMNLP2024 in Miami 🌴.
-
08/29/2024
Giving a talk at Responsible AI for Health Symposium (RAIHS) on MediQ.
-
08/02/2024
Giving a talk at MSR Real-world Evidence Lab on MediQ.
-
07/02/2024
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.
-
06/03/2024
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!
-
12/06/2023
I will be attending EMNLP 2023 in person. Looking forward to meeting everyone in Singapore!
-
04/15/2023
I will be starting my Ph.D. at the University of Washington, excited to be part of Tsvetshop!
-
12/20/2022
Check out our new paper "A Quantitative Approach to Understand Self-Supervised Models as Cross-lingual Feature Extractors."
-
11/14/2022
Check out our new paper "Language Agnostic Code-Mixing Data Augmentation by Predicting Linguistic Patterns."
-
10/21/2022
Check out our new paper "A New Approach to Extract Fetal Electrocardiogram Using Affine Combination of Adaptive Filters."
-
10/07/2022
Check out our new paper "PQLM - Multilingual Decentralized Portable Quantum Language Model for Privacy Protection."
-
09/26/2022
Check out our new paper "End-to-End Lyrics Recognition with Self-supervised Learning."
-
07/09/2022
Check out our workshop paper "Genetic improvement in the shackleton framework for optimizing LLVM pass sequences" accepted to GECCO'22. Best Presentation Award
-
03/24/2022
Check out our paper "Optimizing LLVM Pass Sequences with Shackleton: A Linear Genetic Programming Framework" accepted to GECCO'22.