PrivUn shows privacy unlearning in LLMs produces gradient-driven ripple effects and only shallow forgetting across layers, with new strategies proposed for deeper removal.
The Enron Corpus: A New Dataset for Email Classification Research,
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
roles
dataset 1polarities
use dataset 1representative citing papers
Anonymization placement in RAG—at the dataset or at the generated answer—creates observable differences in privacy protection versus response utility.
GPT-NeoX-20B is a publicly released 20B parameter autoregressive language model trained on the Pile that shows strong gains in five-shot reasoning over similarly sized prior models.
Machine learning classifier for phishing emails reaches 0.99 F1 on a public dataset and is packaged as a web app with XAI.
citing papers explorer
-
PrivUn: Unveiling Latent Ripple Effects and Shallow Forgetting in Privacy Unlearning
PrivUn shows privacy unlearning in LLMs produces gradient-driven ripple effects and only shallow forgetting across layers, with new strategies proposed for deeper removal.
-
A Case Study on the Impact of Anonymization Along the RAG Pipeline
Anonymization placement in RAG—at the dataset or at the generated answer—creates observable differences in privacy protection versus response utility.
-
GPT-NeoX-20B: An Open-Source Autoregressive Language Model
GPT-NeoX-20B is a publicly released 20B parameter autoregressive language model trained on the Pile that shows strong gains in five-shot reasoning over similarly sized prior models.
-
Novel Interpretable and Robust Web-based AI Platform for Phishing Email Detection
Machine learning classifier for phishing emails reaches 0.99 F1 on a public dataset and is packaged as a web app with XAI.