Hello! I am a fourth-year PhD student in computer science at the University of Washington, advised by Yejin Choi and Noah Smith. My research interests include decoding-time algorithms for text generation, dataset creation, and ambiguity in language. I am supported by the NSF Graduate Research Fellowship.

Previously I was an undergraduate at Northwestern University where I majored in computer science and math. There, I was super fortunate to learn about the world of research through natural language processing and computer audition with Professor Doug Downey, Professor Bryan Pardo, and Dr. Prem Seetharaman.

Education
  • PhD student, 2020 - present

    University of Washington

  • BA in Computer Science, Mathematics, 2020

    Northwestern University

Publications

Tuning Language Models by Proxy.
Preprint 2024.

Paper BibTeX Code

We're Afraid Language Models Aren't Modeling Ambiguity.
EMNLP 2023.

Paper BibTeX Code Dataset

That was the last straw, we need more: Are Translation Systems Sensitive to Disambiguating Context?.
EMNLP Findings 2023.

Paper BibTeX Code

Inverse Scaling: When Bigger Isn't Better.
TMLR 2023.

Paper BibTeX Code

Self-Instruct: Aligning Language Models with Self-Generated Instructions.
ACL 2023.

Paper BibTeX Code

Detoxifying Text with MaRCo: Controllable Revision with Experts and Anti-Experts.
ACL 2023.

Paper BibTeX

Generated Knowledge Prompting for Commonsense Reasoning.
ACL 2022.

Paper BibTeX Code

DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts.
ACL 2021.

Paper BibTeX Code Slides News

Model Selection for Deep Audio Source Separation via Clustering Analysis.
DCASE 2020 (Best Student Paper Award).

Paper BibTeX Slides Talk

Bach or Mock? A Grading Function for Chorales in the Style of J.S. Bach.
ML4MD Workshop at ICML 2020.

Paper BibTeX Code Poster

Incorporating Music Knowledge in Continual Dataset Augmentation for Music Generation.
ML4MD Workshop at ICML 2020.

Paper BibTeX Code Poster

CODAH: An Adversarially-Authored Question Answering Dataset for Common Sense.
RepEval Workshop at NAACL 2019.

Paper BibTeX Dataset