Poster "model utility preservation" Papers
4 papers found
MUSE: Machine Unlearning Six-Way Evaluation for Language Models
Weijia Shi, Jaechan Lee, Yangsibo Huang et al.
ICLR 2025posterarXiv:2407.06460
157
citations
Reinforcement Learning with Backtracking Feedback
Bilgehan Sel, Vaishakh Keshava, Phillip Wallis et al.
NeurIPS 2025poster
Ditto: Quantization-aware Secure Inference of Transformers upon MPC
Haoqi Wu, Wenjing Fang, Yancheng Zheng et al.
ICML 2024poster
To Each (Textual Sequence) Its Own: Improving Memorized-Data Unlearning in Large Language Models
George-Octavian Bărbulescu, Peter Triantafillou
ICML 2024poster