About Me

I am a final year PhD candidate in the Department of Computer Science at the University of Virginia, advised by Dr. Yangfeng Ji. My research lies at the intersection of natural language processing (NLP) and machine learning, with an emphasis on large language models (LLMs).

Broadly, I am interested in making NLP systems more reliable, performant, and explainable. My work takes a data-centric perspective, investigating how the quality, structure, and selection of data shapes model behavior and performance. I am especially interested in understanding why models succeed or fail, identifying and mitigating harmful sensitivities and shortcuts, and developing ways to evaluate and improve LLMs to better reflect human needs and judgments.

Prior to starting my PhD at UVA, I completed my undergraduate studies at St. Mary's College of Maryland, graduating summa cum laude with a double major in Computer Science and Psychology.

Updates

  • [08/2025] One paper accepted to EMNLP 2025.
  • [03/2025] One paper accepted to the Insights Workshop at NAACL 2025.
  • [01/2025] One paper accepted to NAACL 2025.
  • [01/2024] I am co-instructing CS 4710: Artificial Intelligence at UVA this semester.
  • [11/2023] Gave an invited talk at the UVA AIML Seminar: "Data Contribution Estimation for Large Language Models".
  • [11/2023] I was awarded the UVA Engineering Teaching Fellow program (TFP) for Spring 2024.
  • [08/2023] Our tutorial "Data Contribution Estimation for Machine Learning" was accepted for NeurIPS 2023.
  • [06/2023] One paper accepted to ACL SRW 2023.
  • [04/2023] Invited panelist on the Graduate School Panel at CAPWIC 2023.
  • [01/2023] Released Python data valuation package: Valda.
  • [01/2023] One paper accepted to Northern European Journal of Language Technology.
  • [10/2022] Received a NeurIPS 2022 Scholar Award.
  • [10/2022] Received the award for Best Poster (Session 1) at the UVA Computer Science Graduate Student Group 2022 Research Symposium.
  • [09/2022] One paper accepted to NeurIPS 2022.
  • [09/2021] Our paper "Underreporting of errors in NLG output, and what to do about it" received the Commendation for Outstanding Position Paper at INLG 2021.
  • [07/2021] Two papers accepted to the International Conference on Natural Language Generation (INLG) 2021.
  • [06/2021] Started a research internship (Summer 2021) with the Query Understanding Team at Walmart Labs.
  • [11/2020] One paper accepted to the Workshop on Evaluating NLG Evaluation at INLG 2020.
  • [10/2020] Invited panelist on the Georgetown University GuWeCode Graduate School Panel.
  • [10/2019] Attended the Grace Hopper Celebration (GHC) as a GHC Scholar.
  • [08/2019] Started Computer Science PhD Program at the University of Virginia.