Omar Mahmoud

3 papers · 2023–2026 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🐣 Hot Topic Early Bird 📈 Trend Setter

Venues

EACL (1) EMNLP (1) NAACL (1)

Top co-authors

Santu Rana (2) Sherif Saad (2) Buddhika Laknath Semage (1) Ali Khalil (1) Hyunwoo Kim (1) Yulia Tsvetkov (1) Thommen George Karimpanal (1) Aly Kassem (1) Yejin Choi (1) Niloofar Mireshghallah (1)

Research topics

Artificial Intelligence (3) Core AI (3) Machine Learning (2) Application Areas (2) Deep Learning (1) Reinforcement Learning (1) Learning Types · Machine Learning (1) Learning Types · Deep Learning (1) Methods (1)

Keywords

large language model (2) privacy preservation (1) machine unlearning (1) instruction tuning (1) safety alignment (1) language model (1) hallucination mitigation (1) proximal policy optimization (1) reinforcement learning feedback (1) sparse autoencoder (1) prompt optimization (1) privacy leakage (1) memorization mitigation (1) refusal behavior (1) unlearning technique (1) language model memorization (1) paraphrasing policy (1) reinforcement learning (1) memorization risk (1)

Papers

The Unintended Trade-off of AI Alignment: Balancing Hallucination Mitigation and Safety in LLMs EACL 2026 ALPACA AGAINST VICUNA: Using LLMs to Uncover Memorization of LLMs NAACL 2025 Preserving Privacy Through Dememorization: An Unlearning Technique For Mitigating Memorization Risks In Language Models EMNLP 2023