Taylor Sorensen (he/him)

Hi! My name is Taylor Sorensen. I’m a Computer Science PhD student at the University of Washington, where I’m fortunate to be advised by Yejin Choi. I research natural language processing (NLP) and artificial intelligence (AI) and am especially interested in AI alignment and ethics, large language models, and NLP for social good. I love working with language because I feel it’s the best medium we have for communicating and understanding human intelligence, and I’m passionate about understanding how to make AI/language models work for positive world impact.

Previously, I received my BS in Applied Math and Computer Science at Brigham Young University. I also worked towards an MS, where I worked with David Wingate on a variety of problems ranging from NLP to machine learning to soft robotics until I left to pursue my PhD.

Historically, I’ve worked on a variety of problems ranging from computer vision to RL for soft robotics to ML-based quantitative investing to NLP for drug discovery.


Publications are listed in reverse chronological order. For a list of all publications, see my google scholar profile.

  • Prompt Compression and Contrastive Conditioning for Controllability and Toxicity Reduction in Language Models
    David Wingate, Mohammad Shoeybi, Taylor Sorensen
    Findings of EMNLP 2022
    Paper, Code

  • An Information-theoretic Approach to Prompt Engineering Without Ground Truth Labels
    Taylor Sorensen, Joshua Robinson, Christopher Michael Rytting, Alexander Glenn Shaw, Kyle Jeffrey Rogers, Alexia Pauline Delorey, Mahmoud Khalil, Nancy Fulda, David Wingate
    ACL 2022
    Paper, Code, Presentation

  • Nl-augmenter: A framework for task-sensitive natural language augmentation
    Kaustubh D Dhole, Varun Gangal, Sebastian Gehrmann, …, Taylor Sorensen et al.
    Arxiv Preprint
    Paper, Code

  • Using first principles for deep learning and model-based control of soft robots
    Curtis C Johnson, Tyler Quackenbush, Taylor Sorensen, David Wingate, Marc D Killpack
    Frontiers in Robotics and AI
    Paper, Code

====== Website last updated: Oct 6, 2022