Papers by Omar Mahmoud
Preserving Privacy Through Dememorization: An Unlearning Technique For Mitigating Memorization Risks In Language Models (2023.emnlp-main)
Copied to clipboard
| Challenge: | Large Language models (LLMs) are trained on vast amounts of data, including sensitive information that poses a risk to personal privacy if exposed. |
| Approach: | They propose a novel unlearning approach that utilizes an efficient reinforcement learning feedback loop via proximal policy optimization to incentivize the LLMs to learn a paraphrasing policy to unlearn the pre-training data. |
| Outcome: | The proposed approach surpasses strong baselines and state-of-the-art methods in terms of its ability to generalize and strike a balance between privacy and LLM performance. |
ALPACA AGAINST VICUNA: Using LLMs to Uncover Memorization of LLMs (2025.naacl-long)
Copied to clipboard
Aly M. Kassem, Omar Mahmoud, Niloofar Mireshghallah, Hyunwoo Kim, Yulia Tsvetkov, Yejin Choi, Sherif Saad, Santu Rana
| Challenge: | Existing studies have shown that pre-trained LLMs emit training data up to 150 more often than in regular operation. |
| Approach: | They propose a black-box prompt optimization method where an attacker LLM agent uncovers higher levels of memorization in a victim agent . |
| Outcome: | The proposed method shows 23.7% more overlap with training data compared to state-of-the-art baselines. |
FRAPPE: FRAming, Persuasion, and Propaganda Explorer (2024.eacl-demo)
Copied to clipboard
Ahmed Sajwani, Alaa El Setohy, Ali Mekky, Diana Turmakhan, Lara Hassan, Mohamed El Zeftawy, Omar El Herraoui, Osama Afzal, Qisheng Liao, Tarek Mahmoud
| Challenge: | FRAPPE is a linguistic analysis, persuasion, and propaganda-based news analysis system that analyzes articles for genre, framings, and persulasion techniques. |
| Approach: | They propose a FRAming, Persuasion, and Propaganda Explorer system that analyzes articles for genre, framings, and use of persuation techniques. |
| Outcome: | FRAPPE analyzes articles for genre, framings, and use of persuasion techniques . it also draws comparisons between persulasion and framping strategies adopted by a diverse pool of news outlets and countries across multiple languages for different topics . |
The Unintended Trade-off of AI Alignment: Balancing Hallucination Mitigation and Safety in LLMs (2026.findings-eacl)
Copied to clipboard
| Challenge: | Hallucination in large language models has been studied, but a side effect remains unrecognized . a new study examines the trade-off between truthfulness and safety alignment . |
| Approach: | They propose a method that disentangles hallucination from hallucinian features using sparse autoencoders. |
| Outcome: | The proposed method preserves refusal behavior and task utility while maintaining safety alignment. |