Sherif Saad
3 papers · 2023–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
π Cross-Pollinator (15) π£ Hot Topic Early Bird π Conference Polyglot (3) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (10)
π§
Keyword Pioneer
π±
Topic Pioneer
π
Trend Setter
Conferences
EACL (1)
EMNLP (1)
NAACL (1)
Top co-authors
Keywords
proximal policy optimization
(2)
language model
(2)
machine unlearning
(1)
instruction tuning
(1)
adversarial attack
(1)
reinforcement learning feedback
(1)
prompt optimization
(1)
privacy leakage
(1)
memorization mitigation
(1)
large language model
(1)
unlearning technique
(1)
language model memorization
(1)
paraphrasing policy
(1)
memorization risk
(1)
targeted paraphrasing
(1)
reinforcement learning
(1)
mutual implication score
(1)
privacy preservation
(1)
Papers
ALPACA AGAINST VICUNA: Using LLMs to Uncover Memorization of LLMs
NAACL 2025
Finding a Needle in the Adversarial Haystack: A Targeted Paraphrasing Approach For Uncovering Edge Cases with Minimal Distribution Distortion
EACL 2024
Preserving Privacy Through Dememorization: An Unlearning Technique For Mitigating Memorization Risks In Language Models
EMNLP 2023