4 papers
Subspace Control: Turning Constrained Model Steering into Controllable Spectral Optimization
Yancheng Huang, Changsheng Wang, Chongyu Fan +7
Foundation models, such as large language models (LLMs), are powerful but often require customization before deployment to satisfy practical constraints such as safety, privacy, an…
Powering Up Zeroth-Order Training via Subspace Gradient Orthogonalization
Yicheng Lang, Changsheng Wang, Yihua Zhang +4
Zeroth-order (ZO) optimization provides a gradient-free alternative to first-order (FO) methods by estimating gradients via finite differences of function evaluations, and has rece…
Downgrade to Upgrade: Optimizer Simplification Enhances Robustness in LLM Unlearning
Yicheng Lang, Yihua Zhang, Chongyu Fan +3
Large language model (LLM) unlearning aims to surgically remove the influence of undesired data or knowledge from an existing model while preserving its utility on unrelated tasks.…
Beyond Single-Value Metrics: Evaluating and Enhancing LLM Unlearning with Cognitive Diagnosis
Yicheng Lang, Kehan Guo, Yue Huang +5
Due to the widespread use of LLMs and the rising critical ethical and safety concerns, LLM unlearning methods have been developed to remove harmful knowledge and undesirable capabi…