Sydney Levine
Scholar

Sydney Levine

Google Scholar ID: Yt2H6lwAAAAJ
Visiting Research Scientist, Google Deepmind
moral psychologycognitive scienceAI safetyAI ethics
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
1,209
 
H-index
14
 
i10-index
20
 
Publications
20
 
Co-authors
36
list available
Contact
CVOpen ↗
Publications
10 items
PluriHarms: Benchmarking the Full Spectrum of Human Judgments on AI Harm
2026
Cited
0
Full-Stack Alignment: Co-Aligning AI and Institutions with Thick Models of Value
2025
Cited
1
MoReBench: Evaluating Procedural and Pluralistic Moral Reasoning in Language Models, More than Outcomes
2025
Cited
0
Resource Rational Contractualism Should Guide AI Alignment
2025
Cited
0
Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas
2025
Cited
0
Hypothesis-Driven Theory-of-Mind Reasoning for Large Language Models
2025
Cited
0
Imagining and building wise machines: The centrality of AI metacognition
arXiv.org · 2024
Cited
4
SafetyAnalyst: Interpretable, transparent, and steerable safety moderation for AI behavior
2024
Cited
0
Resume (English only)
Co-authors
36 total
Joshua B. Tenenbaum
Joshua B. Tenenbaum
MIT
Max Kleiman-Weiner
Max Kleiman-Weiner
University of Washington
Yejin Choi
Yejin Choi
Stanford University / NVIDIA
Iyad Rahwan
Iyad Rahwan
Center for Humans & Machines, Max Planck Institute for Human Development
Edmond Awad
Edmond Awad
Department of Economics, University of Exeter Business School
Co-author 6
Co-author 6
Maarten Sap
Maarten Sap
Carnegie Mellon University
Liwei Jiang
Liwei Jiang
PhD Candidate @ University of Washington