Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning
- Changsheng Wang
- Yihua Zhang
- et al.
- 2025
- ICML 2025
Publications
4 results for Jinghan Jia
WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models
- Jinghan Jia
- Jiancheng Liu
- et al.
- 2024
- NeurIPS 2024
Model Sparsity Can Simplify Machine Unlearning
- Jinghan Jia
- Jiancheng Liu
- et al.
- 2023
- NeurIPS 2023
How to Robustify Black-Box ML Models? A Zeroth-Order Optimization Perspective
- Yimeng Zhang
- Yuguang Yao
- et al.
- 2022
- ICLR 2022