Jaehun Jung

Jaehun Jung is a PhD student in Computer Science and Engineering at the University of Washington, advised by Yejin Choi, and a Student Researcher at NVIDIA Research working on data synthesis and quality estimation for frontier language models. He is known for his research on training and evaluating language models with other models, including work on LLM judges with provable guarantees for human agreement, information-theoretic distillation, and data diversification methods for reasoning. His work has been published at venues including ICLR, NAACL, EMNLP, and COLM.