(she/her/hers)
University of Washington
Natural Language Processing, Language Modeling, Knowledge Extraction
Sewon Min is a Ph.D. student in the Paul G. Allen School of Computer Science & Engineering at the University of Washington, and a part-time visiting researcher at Meta AI. Her research is in the area of natural language processing and machine learning. She was a co-organizer of multiple workshops and tutorials at ACL, EMNLP, NeurIPS, and AKBC, including a workshop on Machine Reading for Question Answering, a workshop on Representation Learning for NLP, a workshop on Semiparametric Methods in NLP, and a tutorial on Zero- and Few-shot Learning with Pretrained Language Models. Prior to UW, she obtained a B.S. degree in Computer Science & Engineering from Seoul National University.
Understanding and Improving Learning through Inference with Large Language Models
Language models are capable of "learning at inference" (also referred to as in-context learning) – learning a new task by conditioning on k examples and making a prediction for a new input with no parameter updates. While impressive, models suffer from high variance and low worst-case accuracy. Moreover, we do not understand how or why in-context learning works. First, I will introduce new methods that lead to significant performance gains by reducing variance and improving worst-case accuracy. I will then show that in-context learning in fact works very differently from conventional learning: the model does not benefit from the correctly paired training data, but rather benefit from the correct specification of the independent distribution of inputs and labels. Finally, I will conclude the talk with lessons learned, limitations, and avenues for future work.