Cover Image

Downgrade to Upgrade: Optimizer Simplification Enhances Robustness in LLM Unlearning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lang, Yicheng, Zhang, Yihua, Fan, Chongyu, Wang, Changsheng, Jia, Jinghan, Liu, Sijia
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond
by: Fan, Chongyu, et al.
Published: (2025)

Reasoning Model Unlearning: Forgetting Traces, Not Just Answers, While Preserving Reasoning Skills
by: Wang, Changsheng, et al.
Published: (2025)

Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning
by: Fan, Chongyu, et al.
Published: (2024)

LLM Unlearning on Noisy Forget Sets: A Study of Incomplete, Rewritten, and Watermarked Data
by: Wang, Changsheng, et al.
Published: (2025)

LLM Unlearning Under the Microscope: A Full-Stack View on Methods and Metrics
by: Fan, Chongyu, et al.
Published: (2025)

Position: Zeroth-Order Optimization in Deep Learning Is Underexplored, Not Underpowered
by: Liu, Sijia, et al.
Published: (2026)

Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning
by: Wang, Changsheng, et al.
Published: (2025)

SOUL: Unlocking the Power of Second-Order Optimization for LLM Unlearning
by: Jia, Jinghan, et al.
Published: (2024)

WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models
by: Jia, Jinghan, et al.
Published: (2024)

SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation
by: Fan, Chongyu, et al.
Published: (2023)

Subspace Control: Turning Constrained Model Steering into Controllable Spectral Optimization
by: Huang, Yancheng, et al.
Published: (2026)

Powering Up Zeroth-Order Training via Subspace Gradient Orthogonalization
by: Lang, Yicheng, et al.
Published: (2026)

SEUF: Is Unlearning One Expert Enough for Mixture-of-Experts LLMs?
by: Zhuang, Haomin, et al.
Published: (2024)

Unlearners Can Lie: Evaluating and Improving Honesty in LLM Unlearning
by: Gu, Renjie, et al.
Published: (2026)

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation
by: Jia, Jinghan, et al.
Published: (2025)

Challenging Forgets: Unveiling the Worst-Case Forget Sets in Machine Unlearning
by: Fan, Chongyu, et al.
Published: (2024)

BLUR: A Bi-Level Optimization Approach for LLM Unlearning
by: Reisizadeh, Hadi, et al.
Published: (2025)

Forget Vectors at Play: Universal Input Perturbations Driving Machine Unlearning in Image Classification
by: Sun, Changchang, et al.
Published: (2024)

Forgetting to Forget: Attention Sink as A Gateway for Backdooring LLM Unlearning
by: Shang, Bingqi, et al.
Published: (2025)

Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models
by: Zhang, Yimeng, et al.
Published: (2024)

LLM Unlearning Reveals a Stronger-Than-Expected Coreset Effect in Current Benchmarks
by: Pal, Soumyadeep, et al.
Published: (2025)

One Token Embedding Is Enough to Deadlock Your Large Reasoning Model
by: Zhang, Mohan, et al.
Published: (2025)

Model Sparsity Can Simplify Machine Unlearning
by: Jia, Jinghan, et al.
Published: (2023)

CyclicReflex: Improving Reasoning Models via Cyclical Reflection Token Scheduling
by: Fan, Chongyu, et al.
Published: (2025)

Label Smoothing Improves Machine Unlearning
by: Di, Zonglin, et al.
Published: (2024)

Beyond Single-Value Metrics: Evaluating and Enhancing LLM Unlearning with Cognitive Diagnosis
by: Lang, Yicheng, et al.
Published: (2025)

DeepZero: Scaling up Zeroth-Order Optimization for Deep Model Training
by: Chen, Aochuan, et al.
Published: (2023)

UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in Diffusion Models
by: Zhang, Yihua, et al.
Published: (2024)

The Power of Few: Accelerating and Enhancing Data Reweighting with Coreset Selection
by: Jafari, Mohammad, et al.
Published: (2024)

Visual Prompting Upgrades Neural Network Sparsification: A Data-Model Perspective
by: Jin, Can, et al.
Published: (2023)

Safety Mirage: How Spurious Correlations Undermine VLM Safety Fine-Tuning and Can Be Mitigated by Machine Unlearning
by: Chen, Yiwei, et al.
Published: (2025)

Rethinking Muon Beyond Pretraining: Spectral Failures and High-Pass Remedies for VLA and RLVR
by: Fan, Chongyu, et al.
Published: (2026)

Breaking Memorization Barriers in LLM Code Fine-Tuning via Information Bottleneck for Improved Generalization
by: Wang, Changsheng, et al.
Published: (2025)

Continual Unlearning for Text-to-Image Diffusion Models: A Regularization Perspective
by: Lee, Justin, et al.
Published: (2025)

Unlearning Isn't Invisible: Detecting Unlearning Traces in LLMs from Model Outputs
by: Chen, Yiwei, et al.
Published: (2025)

Harmonizing Multi-Objective LLM Unlearning via Unified Domain Representation and Bidirectional Logit Distillation
by: Zhong, Yisheng, et al.
Published: (2026)

LEKA:LLM-Enhanced Knowledge Augmentation
by: Zhang, Xinhao, et al.
Published: (2025)

Unlearning Concepts from Text-to-Video Diffusion Models
by: Liu, Shiqi, et al.
Published: (2024)

Rethinking Machine Unlearning for Large Language Models
by: Liu, Sijia, et al.
Published: (2024)

Exploring Criteria of Loss Reweighting to Enhance LLM Unlearning
by: Yang, Puning, et al.
Published: (2025)