Papers by Aly Kassem

2 papers
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.
Finding a Needle in the Adversarial Haystack: A Targeted Paraphrasing Approach For Uncovering Edge Cases with Minimal Distribution Distortion (2024.eacl-long)

Copied to clipboard

Challenge: Adversarial attacks against Language models (LMs) are a significant concern.
Approach: They propose an approach to automatically learn a policy to generate challenging examples that improve the model’s performance.
Outcome: The proposed approach outperforms baselines and exhibits generalizability across classifiers and datasets.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations