2024ReviewedOpen access
Machine Unlearning in Generative AI: A Survey
Zheyuan Liu, Guangyao Dou, Zhaoxuan Tan, Yijun Tian, Meng Jiang
arXiv preprint
Abstract
Surveys machine unlearning techniques for LLMs including methods for forgetting specific training data, complying with data deletion requests, and maintaining model utility.
Categories
#machine-unlearning#right-to-erasure#GDPR
Framework mappings
NIST AI Risk Management Framework
- GOVERNGovern
- MANAGEManage
ISO/IEC 42001
- 8Operation
Cite
@misc{liu2024machine,
title = {{Machine Unlearning in Generative AI: A Survey}},
author = {Zheyuan Liu and Guangyao Dou and Zhaoxuan Tan and Yijun Tian and Meng Jiang},
year = {2024},
eprint = {2407.20516},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2407.20516}
}