About me

I am a first-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

    • design icon

      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?

    • design icon

      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

    1. 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.

    2. 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!

    3. 12/06/2023

      I will be attending EMNLP 2023 in person. Looking forward to meeting everyone in Singapore!

    4. 04/15/2023

      I will be starting my Ph.D. at the University of Washington, excited to be part of Tsvetshop!

    5. 12/20/2022

      Check out our new paper "A Quantitative Approach to Understand Self-Supervised Models as Cross-lingual Feature Extractors."

    6. 11/14/2022

      Check out our new paper "Language Agnostic Code-Mixing Data Augmentation by Predicting Linguistic Patterns."

    7. 10/21/2022

      Check out our new paper "A New Approach to Extract Fetal Electrocardiogram Using Affine Combination of Adaptive Filters."

    8. 10/07/2022

      Check out our new paper "PQLM - Multilingual Decentralized Portable Quantum Language Model for Privacy Protection."

    9. 09/26/2022

      Check out our new paper "End-to-End Lyrics Recognition with Self-supervised Learning."

    10. 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

    11. 03/24/2022

      Check out our paper "Optimizing LLVM Pass Sequences with Shackleton: A Linear Genetic Programming Framework" accepted to GECCO'22.

    Experience

  • Click here to view my CV (updated Sep. 23)

     
  • Education

    1. University of Washington

      2023 — present | Seattle, WA

      Ph.D. in Computer Science and Engineering

      Advised by Yulia Tsvetkov.

    2. Johns Hopkins University

      2019 — 2023 | Baltimore, MD

      B.S. & M.S.E. in Computer Science

      Advised by Philipp Koehn and Kenton Murray.

      Thesis: Learning from Gibberish: Code-Mixing Data Augmentation for Sentiment Analysis

      Other Majors: Cognitive Science (linguistics focus), Applied Mathematics (statistics focus)

      Minor: Mathematics

      Cumulative GPA: 3.99/4.0, Major GPA: 4.0/4.0

    3. Stanford Online High School

      2018 — 2019 | Palo Alto, CA

      Dual enrollment program with a focus in advanced mathematics

      GPA (unweighted): 4.0/4.0

    4. Robert Louis Stevenson School

      2016 — 2019 | Pebble Beach, CA

      Awards & Leadership: Cum Laude Society, USABO Semifinalist, USAMO Qualified, Bausch & Lomb National Science Award, Math Madness Silver Medalist, Math Team Captain, Spanish National Honor Society, Varsity Volleyball

      GPA (unweighted): 3.98/4.0

    Teaching/TA Experience

    1. Introduction to Statistics: Teaching Assistant

      2020 Spring, 2021 Fall, 2022 Spring, 2023 Spring

      EN.503.430 (undergrad) & EN.503.630 (grad) & EN.503.431 (honors)

    2. Artificial Intelligence: Course Assistant

      2023 Spring

      EN.601.464 (undergrad) & EN.601.664 (grad)

    3. Human-Computer Interaction: Course Assistant

      2022 Fall

      EN.601.490 (undergrad) & EN.601.690 (grad)

    4. Computer Ethics: Head Course Assistant

      2022 Summer

      EN.601.104

    5. Intermediate Programming: Course Assistant

      2020 Spring, 2021 Fall, 2022 Spring

      EN.601.220

    Work Experience

    1. Yext: Software Engineering Intern

      2022 Summer | Arlington, VA

      Integrated client data to Yext platform for real-time site information updates using Go.

      Created a Figma Style Picker to improve developer workflow and scalability using ReactJS.

    2. Michigan State University: Research Intern

      2021 Summer | East Lansing, MI

      Advised by Wolfgang Banzhaf.

      Designed and implemented novel GP algorithm for LLVM compiler flag optimization (20%).

      Published work at GECCO; second author of GP paper; first author of GI paper.

    3. Bytedance AI Lab: Research Intern

      2020 Summer | Beijing, China

      Trained neural networks for text normalization in text-to-speech tasks.

      Implemented statistical information-retrieval algorithms for theme clustering and complexity ranking for TikTok videos.

    4. Johns Hopkins Language and Cognition Lab: Research Assistant

      2020 - 2022 | Baltimore, MD

      Advised by Barbara Landau.

      Investigated developmental spatial cognition using Lego Block building.

      Created ML model for movement prediction and stability analysis using motion sensor data.

    5. IBM AI Doctor: Data Science Intern

      2019 Summer | Beijing, China

      Created ML models to predict diseases diagnosis from symptoms using EHR records.

      Improved classification accuracy from 74% to 99% with a hybrid algorithm of GA with SVM.

    Publications

    Photography