Get started
Author

Narmeen Fatimah Oozeer

Observed names: Narmeen Oozeer, Oozeer, Narmeen, Oozeer, Narmeen Fatimah
Institution: University of Utah
OpenAlex ID: A5119862711
Are LLM Evaluators Really Narcissists? Sanity Checking Self-Preference Evaluations
2026 · Roytburg, Dani, Bozoukov, Matthew, et al. · arXiv (Cornell University) · 2
PDF
Activation Space Interventions Can Be Transferred Between Large Language Models
2025 · Oozeer, Narmeen, Nathawani, Dhruv, et al. · arXiv (Cornell University) · 1
PDF
Beyond Linear Steering: Unified Multi-Attribute Control for Language Models
2025 · Narmeen Fatimah Oozeer, Luke Marks, et al. · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · 1
PDF
Orthogonal and Parametrized Multi-Attribute Steering of LLMs
2026 · Ogasawara, Remy, Anderson, Cullen, et al. · arXiv (Cornell University)
PDF
What Accuracy Hides In Learned Transformer Programs
2026 · Lee, Jonathan, Oozeer, Narmeen, et al. · arXiv (Cornell University)
PDF
Judging by the Cover: Cleaning LLM Truthfulness Benchmarks to Avoid Surface-Level Feature Leakage
2026 · Namjoo, Foad, Ogasawara, Remy, et al. · arXiv (Cornell University)
PDF
The Capability Frontier: Benchmarks Miss 82% of Model Performance
2026 · Fowler, Bradley, Smith, Ryan, et al. · arXiv (Cornell University)
PDF
Make Mechanistic Interpretability Auditable: A Call to Develop Guidelines via Continuous Collaborative Reviewing
2026 · Association for Computational Linguistics 2026, Abdullah, Amir, et al. · Underline Science Inc.
Riemannian-Manifold Steering: Geometry-Aware Generative Autoencoders for Label-Free Steering
2026 · Oozeer, Narmeen, Raval, Shivam, et al. · arXiv (Cornell University)
PDF
Geometry-Aware CLIP Retrieval via Local Cross-Modal Alignment and Steering
2026 · Prakash, Nirmalendu, Oozeer, Narmeen Fatimah, et al. · arXiv (Cornell University)
PDF
Understanding and Mitigating Dataset Corruption in LLM Steering
2026 · Anderson, Cullen, Oozeer, Narmeen, et al. · arXiv (Cornell University)
PDF
DreamReader: An Interpretability Toolkit for Text-to-Image Models
2026 · Prakash, Nirmalendu, Oozeer, Narmeen, et al. · arXiv (Cornell University)
PDF
Spectral Superposition: A Theory of Feature Geometry
2026 · Ivanov, Georgi, Oozeer, Narmeen, et al. · arXiv (Cornell University)
PDF
Make Mechanistic Interpretability Auditable: A Call to Develop Guidelines via Continuous Collaborative Reviewing
2026 · Michael Lan, Narmeen Fatimah Oozeer, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting
PDF
Distribution-Aware Feature Selection for SAEs
2025 · Oozeer, Narmeen, Prakash, Nirmalendu, et al. · arXiv (Cornell University)
PDF
Beyond Monoliths: Expert Orchestration for More Capable, Democratic, and Safe Language Models
2025 · Quirke, Philip, Oozeer, Narmeen, et al. · arXiv (Cornell University)
PDF
Position: Require Frontier AI Labs To Release Small "Analog" Models
2025 · Shriyash Upadhyay, Philip Quirke, et al. · neural information processing systems
Works count: 20
Citation count: 4
H-index: 1
I10-index:
Year
Topic
Type