Sewon Min

Sewon Min is an Assistant Professor at UC Berkeley's Electrical Engineering and Computer Sciences (EECS) department and a research scientist at the Allen Institute for AI. Her research focuses on Natural Language Processing (NLP) and Machine Learning, particularly Large Language Models (LLMs), emphasizing data-centric approaches and ethical AI practices. She holds a Ph.D. from the University of Washington (2024) and a B.S. from Seoul National University (2018).

Her work includes advancements in retrieval-based models, mixture-of-experts architectures, and data privacy in LLMs. Notable projects include FlexOlmo (flexible data use in LLMs) and OLMoE (open mixture-of-experts models). She has been recognized with the ACM Doctoral Dissertation Award Honorable Mention (2025) and WAGS/ProQuest Innovation in Technology Award.

Recent articles highlight her contributions to reasoning models, data tracing (OLMoTrace), and scalable retrieval systems (MassiveDS). She leads the Berkeley NLP Group and collaborates with BAIR, exploring topics like model transparency and ethical data usage.