"model utility preservation" Papers
5 papers found
Conference
MUSE: Machine Unlearning Six-Way Evaluation for Language Models
Weijia Shi, Jaechan Lee, Yangsibo Huang et al.
ICLR 2025arXiv:2407.06460
168
citations
Reinforcement Learning with Backtracking Feedback
Bilgehan Sel, Vaishakh Keshava, Phillip Wallis et al.
NEURIPS 2025
Targeted Unlearning with Single Layer Unlearning Gradient
Zikui Cai, Yaoteng Tan, M. Salman Asif
ICML 2025arXiv:2407.11867
3
citations
Ditto: Quantization-aware Secure Inference of Transformers upon MPC
Haoqi Wu, Wenjing Fang, Yancheng Zheng et al.
ICML 2024arXiv:2405.05525
16
citations
To Each (Textual Sequence) Its Own: Improving Memorized-Data Unlearning in Large Language Models
George-Octavian Bărbulescu, Peter Triantafillou
ICML 2024