Princeton University
Stanford University
Long OuyangResearch Scientist · OpenAIResearcher↗EM
Researcher · Engineer
Eric Mitchell
OpenAIMember of Technical Staff
Mitchell co-leads OpenAI's Post-training Frontiers team, which trained and deployed o1, o3 and GPT-5 Thinking. His earlier research developed direct preference optimization, a simpler way to align language models with human choices, alongside methods for factuality and editing model knowledge.
Career & education
Current roleOpenAI2024-presentMember of Technical Staff
OpenAI2024-presentPreviously
Samsung Research America2018-2019
Machine Learning Research EngineerWork and education history is primarily focused on AI-relevant roles and may not be comprehensive.
Citation Trend
Total citations to scholarly work, including research papers, technical reports, books and theses, as recorded by Google Scholar. Each point is a dated snapshot.
citations20,627As of Jun 14, '26
Selected contributions
Direct Preference Optimization: Your Language Model is Secretly a Reward Model
DPO trains language models directly on comparisons of preferred and rejected answers.
Based on public sources. If accuracy is important, verify details using the links or references.
For corrections, updates, or requests to remove information, contact us.
Reviewed August 10, 2026 · Checked for accuracy and new information.
