TRACER uses token reassignment for concept-related items plus a coherence regularizer to unlearn specific concepts in generative recommendation while preserving utility better than baselines.
Towards llm unlearning resilient to relearning attacks: A sharpness-aware minimization perspective and beyond
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
Introduces Unlearning Depth Score (UDS) via activation patching to quantify LLM unlearning depth and claims it outperforms 20 other metrics in faithfulness and robustness on 150 models.
A unified adaptive attack exploits the common weakness across 15 defenses against malicious fine-tuning, showing they only obscure rather than remove harmful model capabilities.
The Influence Eliminating Unlearning framework maximizes relearning convergence delay via weight decay and noise injection to remove the influence of a forgetting set while preserving accuracy on retained data.
CURE disentangles LLM recommendation circuits into forget-specific, retain-specific, and task-shared modules with tailored update rules to achieve more effective unlearning than weighted baselines.
Downgrading optimizers to lower-information variants during LLM unlearning yields more robust forgetting on MUSE and WMDP benchmarks by converging to harder-to-perturb loss basins.
BARRIER applies interval arithmetic to SVD-based activation projections to create bounded forget regions that enable aggressive unlearning while providing formal protection for retain distributions via tail bounds on functional drift.
citing papers explorer
-
TRACER: Token ReAssignment for Concept ERasure in Generative Recommendation
TRACER uses token reassignment for concept-related items plus a coherence regularizer to unlearn specific concepts in generative recommendation while preserving utility better than baselines.
-
Measuring the Depth of LLM Unlearning via Activation Patching
Introduces Unlearning Depth Score (UDS) via activation patching to quantify LLM unlearning depth and claims it outperforms 20 other metrics in faithfulness and robustness on 150 models.
-
One Step to the Side: Why Defenses Against Malicious Finetuning Fail Under Adaptive Adversaries
A unified adaptive attack exploits the common weakness across 15 defenses against malicious fine-tuning, showing they only obscure rather than remove harmful model capabilities.
-
Efficient Unlearning through Maximizing Relearning Convergence Delay
The Influence Eliminating Unlearning framework maximizes relearning convergence delay via weight decay and noise injection to remove the influence of a forgetting set while preserving accuracy on retained data.
-
CURE:Circuit-Aware Unlearning for LLM-based Recommendation
CURE disentangles LLM recommendation circuits into forget-specific, retain-specific, and task-shared modules with tailored update rules to achieve more effective unlearning than weighted baselines.
-
Downgrade to Upgrade: Optimizer Simplification Enhances Robustness in LLM Unlearning
Downgrading optimizers to lower-information variants during LLM unlearning yields more robust forgetting on MUSE and WMDP benchmarks by converging to harder-to-perturb loss basins.
-
BARRIER: Bounded Activation Regions for Robust Information Erasure
BARRIER applies interval arithmetic to SVD-based activation projections to create bounded forget regions that enable aggressive unlearning while providing formal protection for retain distributions via tail bounds on functional drift.