Cover Image

Dual-Space Smoothness for Robust and Balanced LLM Unlearning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yan, Han, Liu, Zheyuan, Jiang, Meng
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Machine Unlearning in Generative AI: A Survey
by: Liu, Zheyuan, et al.
Published: (2024)

Robust LLM Unlearning with MUDMAN: Meta-Unlearning with Disruption Masking And Normalization
by: Sondej, Filip, et al.
Published: (2025)

Attention Smoothing Is All You Need For Unlearning
by: Zade, Saleh Zare, et al.
Published: (2026)

A Comprehensive Evaluation of LLM Unlearning Robustness under Multi-Turn Interaction
by: Pan, Ruihao, et al.
Published: (2026)

Catastrophic Failure of LLM Unlearning via Quantization
by: Zhang, Zhiwei, et al.
Published: (2024)

UniErase: Towards Balanced and Precise Unlearning in Language Models
by: Yu, Miao, et al.
Published: (2025)

MEOW: MEMOry Supervised LLM Unlearning Via Inverted Facts
by: Gu, Tianle, et al.
Published: (2024)

Prompt-Activation Duality: Improving Activation Steering via Attention-Level Interventions
by: Kang, Diancheng, et al.
Published: (2026)

Agents Are All You Need for LLM Unlearning
by: Sanyal, Debdeep, et al.
Published: (2025)

Reversing the Forget-Retain Objectives: An Efficient LLM Unlearning Framework from Logit Difference
by: Ji, Jiabao, et al.
Published: (2024)

Collapse of Irrelevant Representations (CIR) Ensures Robust and Non-Disruptive LLM Unlearning
by: Sondej, Filip, et al.
Published: (2025)

Steering Multimodal Large Language Models Decoding for Context-Aware Safety
by: Liu, Zheyuan, et al.
Published: (2025)

Protecting Privacy in Multimodal Large Language Models with MLLMU-Bench
by: Liu, Zheyuan, et al.
Published: (2024)

MTMCS-Bench: Evaluating Contextual Safety of Multimodal Large Language Models in Multi-Turn Dialogues
by: Liu, Zheyuan, et al.
Published: (2026)

UPCORE: Utility-Preserving Coreset Selection for Balanced Unlearning
by: Patil, Vaidehi, et al.
Published: (2025)

LLM Unlearning Without an Expert Curated Dataset
by: Zhu, Xiaoyuan, et al.
Published: (2025)

Advancing the Robustness of Large Language Models through Self-Denoised Smoothing
by: Ji, Jiabao, et al.
Published: (2024)

Unlearned but Not Forgotten: Data Extraction after Exact Unlearning in LLM
by: Wu, Xiaoyu, et al.
Published: (2025)

Smooth Reading: Bridging the Gap of Recurrent LLM to Self-Attention LLM on Long-Context Tasks
by: Liu, Kai, et al.
Published: (2025)

From Domains to Instances: Dual-Granularity Data Synthesis for LLM Unlearning
by: Xu, Xiaoyu, et al.
Published: (2026)

LLM Unlearning via Loss Adjustment with Only Forget Data
by: Wang, Yaxuan, et al.
Published: (2024)

Explainable LLM Unlearning Through Reasoning
by: Liao, Junfeng, et al.
Published: (2026)

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

DRAGON: Guard LLM Unlearning in Context via Negative Detection and Reasoning
by: Wang, Yaxuan, et al.
Published: (2025)

UNDIAL: Self-Distillation with Adjusted Logits for Robust Unlearning in Large Language Models
by: Dong, Yijiang River, et al.
Published: (2024)

Towards Robust Knowledge Unlearning: An Adversarial Framework for Assessing and Improving Unlearning Robustness in Large Language Models
by: Yuan, Hongbang, et al.
Published: (2024)

CodeUnlearn: Amortized Zero-Shot Machine Unlearning in Language Models Using Discrete Concept
by: Wu, YuXuan, et al.
Published: (2024)

Understanding the Dilemma of Unlearning for Large Language Models
by: Zhang, Qingjie, et al.
Published: (2025)

Issue Localization via LLM-Driven Iterative Code Graph Searching
by: Jiang, Zhonghao, et al.
Published: (2025)

Drift-Bench: Diagnosing Cooperative Breakdowns in LLM Agents under Input Faults via Multi-Turn Interaction
by: Bao, Han, et al.
Published: (2026)

Cyber for AI at SemEval-2025 Task 4: Forgotten but Not Lost: The Balancing Act of Selective Unlearning in Large Language Models
by: P, Dinesh Srivasthav, et al.
Published: (2025)

GRAIL: Gradient-Based Adaptive Unlearning for Privacy and Copyright in LLMs
by: Kim, Kun-Woo, et al.
Published: (2025)

Measuring the Depth of LLM Unlearning via Activation Patching
by: Lee, Jaeung, et al.
Published: (2026)

Uncovering the Potential Risks in Unlearning: Danger of English-only Unlearning in Multilingual LLMs
by: Hwang, Kyomin, et al.
Published: (2025)

Consistency-Aware Editing for Entity-level Unlearning in Language Models
by: Han, Xiaoqi, et al.
Published: (2025)

Fitting Is Not Enough: Smoothness in Extremely Quantized LLMs
by: Xu, Yuzhuang, et al.
Published: (2026)

Harnessing Consistency for Robust Test-Time LLM Ensemble
by: Zeng, Zhichen, et al.
Published: (2025)

Sens-Merging: Sensitivity-Guided Parameter Balancing for Merging Large Language Models
by: Liu, Shuqi, et al.
Published: (2025)

Reveal and Release: Iterative LLM Unlearning with Self-generated Data
by: Xie, Linxi, et al.
Published: (2025)

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