OpenAI
Tsinghua University
Stanford University
Sebastian RuderResearch Scientist · MetaResearcher↗
Researcher
Shengjia Zhao
MetaChief Scientist
Zhao helped shape how language models learn from human feedback. He led GPT-4’s reward-model work, which scores answers to guide training[1], and helped lead GPT-4o mini, a smaller, cheaper model.[2] He was also a foundational contributor to o1[3], which improved reasoning by spending more time working through problems.[4]
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.
citations51,152As of Oct 19, '26
citations+7,494Since last snapshot, Jun 15, '26
Selected contributions
GPT-4 Technical Report
With OpenAI, Joshua Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman and others ·Reported GPT-4's capabilities, limitations and safety evaluations as a text-and-image input model.
References
- GPT-4 contribution creditsopenai.com
Official credits explicitly identify Zhao as reward model lead; human-feedback alignment role.
- GPT-4o mini release and creditsopenai.com
Official release names Zhao among model leads and documents lower cost.
- OpenAI o1 — foundational contributorsopenai.com
Official credits explicitly identify Zhao as foundational contributor to reasoning research.
- Learning to reason with LLMsopenai.com
Original release explains test-time reasoning and improved performance with more thinking time.
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 October 19, 2026 · Checked for accuracy and new information.
