Scholar
Ninareh Mehrabi
Google Scholar ID: 3SfPdIQAAAAJ
Amazon
Citations & Impact
Citations
8,189
H-index
15
i10-index
21
Publications
20
Co-authors
3
list available
Contact
Publications
Resume (English only)
Academic Achievements
- - A Survey on Bias and Fairness in Machine Learning, ACM Computing Surveys (CSUR)
- - FLIRT: Feedback Loop In-context Red Teaming, EMNLP 2024
- - Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation, ACL 2025 Findings
- - DATA ADVISOR: Dynamic Data Curation for Safety Alignment of Large Language Models, EMNLP 2024
- - And other papers published in NAACL, ACL, etc.
Research Experience
- - Senior Research Scientist, Meta Superintelligence Labs
- - Applied Scientist, Amazon AGI
- - Postdoctoral Researcher, Amazon Alexa AI Responsible AI Team
Education
- Ph.D. from University of Southern California's Information Sciences Institute, advisors: Aram Galstyan and Fred Morstatter, part of the MINDS group.
Background
- Senior research scientist at Meta's Superintelligence Labs, working on red teaming and frontier risks. Previously, an applied scientist at Amazon AGI, developing responsible AI systems. Prior to that, a postdoctoral researcher at Amazon Alexa AI's Responsible AI team.
Miscellany
- Invited talk at NSERC Responsible AI (October 2024). My work was featured in Cloudwalkers ISI and the Inventors of the Future documentary.
