Scholar
Long Phan
Google Scholar ID: fVRQn4wAAAAJ
Center for AI Safety
Citations & Impact
Citations
4,743
H-index
14
i10-index
16
Publications
20
Co-authors
4
list available
Publications
Cited
0
Cited
0
Resume (English only)
Academic Achievements
- Published several papers such as 'Humanity's Last Exam', 'Improving Alignment and Robustness with Circuit Breakers', 'HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal', etc. Also contributed to large open-source projects like BLOOM.
Research Experience
- Working at Center for AI Safety, involved in multiple research projects including Humanity's Last Exam, Improving Alignment and Robustness with Circuit Breakers, HarmBench, etc.
Education
- Received a B.S. in Computer Science from Case Western Reserve University in 2023. Worked with Trieu H. Trinh and Minh-Thang Luong (DeepMind) during undergraduate studies.
Background
- Currently a Research Engineer at Center for AI Safety, working with Dan Hendrycks. Interested in AI Safety.
Miscellany
- Ranked 1st in North America for Amumu (3rd globally) and 3rd in North America for Gragas in League of Legends, Season 2023.
