Cover Image

Rethinking Benign Relearning: Syntax as the Hidden Driver of Unlearning Failures

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yoon, Sangyeon, Hong, Hyesoo, Jeung, Wonje, No, Albert
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

VLMs Trace Without Tracking: Diagnosing Failures in Visual Path Following
by: Hong, Hyesoo, et al.
Published: (2026)

Adversarial Sample-Based Approach for Tighter Privacy Auditing in Final Model-Only Scenarios
by: Yoon, Sangyeon, et al.
Published: (2024)

Few-Shot Truly Benign DPO Attack for Jailbreaking LLMs
by: Yoon, Sangyeon, et al.
Published: (2026)

An Information Theoretic Evaluation Metric For Strong Unlearning
by: Jeon, Dongjae, et al.
Published: (2024)

A2D: Any-Order, Any-Step Safety Alignment for Diffusion Language Models
by: Jeung, Wonje, et al.
Published: (2025)

SAFEPATH: Preventing Harmful Reasoning in Chain-of-Thought via Early Alignment
by: Jeung, Wonje, et al.
Published: (2025)

R-TOFU: Unlearning in Large Reasoning Models
by: Yoon, Sangyeon, et al.
Published: (2025)

SEPS: A Separability Measure for Robust Unlearning in LLMs
by: Jeung, Wonje, et al.
Published: (2025)

BenchPreS: A Benchmark for Context-Aware Personalized Preference Selectivity of Persistent-Memory LLMs
by: Yoon, Sangyeon, et al.
Published: (2026)

DUSK: Do Not Unlearn Shared Knowledge
by: Jeung, Wonje, et al.
Published: (2025)

Unlearning's Blind Spots: Over-Unlearning and Prototypical Relearning Attack
by: Ha, SeungBum, et al.
Published: (2025)

FedCARE: Federated Unlearning with Conflict-Aware Projection and Relearning-Resistant Recovery
by: Li, Yue, et al.
Published: (2026)

Unlearn to Relearn Backdoors: Deferred Backdoor Functionality Attacks on Deep Learning Models
by: Shin, Jeongjin, et al.
Published: (2024)

Unlearning or Obfuscating? Jogging the Memory of Unlearned LLMs via Benign Relearning
by: Hu, Shengyuan, et al.
Published: (2024)

Multi-Level Knowledge Distillation and Dynamic Self-Supervised Learning for Continual Learning
by: Kim, Taeheon, et al.
Published: (2025)

NeuRel-Attack: Neuron Relearning for Safety Disalignment in Large Language Models
by: Zhou, Yi, et al.
Published: (2025)

Federated Unlearning in the Wild: Rethinking Fairness and Data Discrepancy
by: Huang, ZiHeng, et al.
Published: (2025)

Memory Self-Regeneration: Uncovering Hidden Knowledge in Unlearned Models
by: Polowczyk, Agnieszka, et al.
Published: (2025)

Forgetting is Competition: Rethinking Unlearning as Representation Interference in Diffusion Models
by: Ranjan, Ashutosh, et al.
Published: (2026)

Rainbow Padding: Mitigating Early Termination in Instruction-Tuned Diffusion LLMs
by: Kim, Bumjun, et al.
Published: (2025)

Layered Unlearning for Adversarial Relearning
by: Qian, Timothy, et al.
Published: (2025)

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

Rethinking RL Evaluation: Can Benchmarks Truly Reveal Failures of RL Methods?
by: Chen, Zihan, et al.
Published: (2025)

Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss
by: Park, Sangyeon, et al.
Published: (2025)

Incremental Learning of Retrievable Skills For Efficient Continual Task Adaptation
by: Lee, Daehee, et al.
Published: (2024)

Distributional Clarity: The Hidden Driver of RL-Friendliness in Large Language Models
by: Sun, Shaoning, et al.
Published: (2026)

Learning Equi-angular Representations for Online Continual Learning
by: Seo, Minhyuk, et al.
Published: (2024)

Benign Overfitting in Adversarial Training for Vision Transformers
by: Zhang, Jiaming, et al.
Published: (2026)

Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning Attacks
by: Di, Jimmy Z., et al.
Published: (2022)

Deep Unlearn: Benchmarking Machine Unlearning for Image Classification
by: Cadet, Xavier F., et al.
Published: (2024)

Rethinking Forward Processes for Score-Based Nonlinear Data Assimilation in High Dimensions
by: Yoon, Eunbi, et al.
Published: (2026)

Low Resource Reconstruction Attacks Through Benign Prompts
by: Yarkoni, Sol, et al.
Published: (2025)

Agentic Unlearning: When LLM Agent Meets Machine Unlearning
by: Wang, Bin, et al.
Published: (2026)

DP2Unlearning: An Efficient and Guaranteed Unlearning Framework for LLMs
by: Mahmud, Tamim Al, et al.
Published: (2025)

Unlearning Information Bottleneck: Machine Unlearning of Systematic Patterns and Biases
by: Han, Ling, et al.
Published: (2024)

On the Emergence of Syntax by Means of Local Interaction
by: Wei, Zichao
Published: (2026)

Rethinking Post-Unlearning Behavior of Large Vision-Language Models
by: Kim, Minsung, et al.
Published: (2025)

Generating Synthetic Fair Syntax-agnostic Data by Learning and Distilling Fair Representation
by: Sikder, Md Fahim, et al.
Published: (2024)

A Classical View on Benign Overfitting: The Role of Sample Size
by: Park, Junhyung, et al.
Published: (2025)

Distillation Robustifies Unlearning
by: Lee, Bruce W., et al.
Published: (2025)