arXiv AI
Measuring the Depth of LLM Unlearning via Activation Patching
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Jun 2
Unlearning Isn't Invisible: Detecting Unlearning Traces in LLMs from Model Outputs
arXiv:2506. 14003v5 Announce Type: replace Abstract: Machine unlearning (MU) for large language models (LLMs), commonly referred to as LLM unlearning, seeks to remove specific undesirable data or knowledge from a trained model, while maintaining its performance on standard tasks.
arXiv Computation and Language
Aug 25
Can LLMs Truly Forget? Revealing Unlearning Gaps Through Adversarial Evaluation
arXiv:2608.21606v1 Announce Type: new Abstract: Machine unlearning aims to remove the influence of targeted training data from a model while preserving its remaining capabilities, but evaluating whet...
arXiv AI
Jul 3
LACUNA: A Testbed for Evaluating Localization Precision for LLM Unlearning
arXiv:2607. 02513v1 Announce Type: cross Abstract: LLMs memorize sensitive training data, including personally identifiable information (PII), creating a pressing need for reliable post hoc removal methods.
arXiv Machine Learning
Jun 16
Auditing Machine Unlearning: A Systematic Research on Whether Models Truly Forget
arXiv:2606. 16110v1 Announce Type: new Abstract: Machine unlearning has been extensively studied in response to growing privacy concerns and regulatory requirements.
arXiv AI
Jun 6
LLMs Can Leak Training Data But Do They Want To? A Propensity-Aware Evaluation of Memorization in LLMs
arXiv:2606. 06286v1 Announce Type: cross Abstract: Large language models can reproduce training data, but existing memorization evaluations mostly measure whether models can be forced to do so, rather than whether they do so under ordinary use.
Hugging Face Trending Papers
Jun 15
Auditing Machine Unlearning: A Systematic Research on Whether Models Truly Forget
Machine unlearning has been extensively studied in response to growing privacy concerns and regulatory requirements. However, auditing whether unlearning algorithms have truly erased the influence of specific data remains an open challenge.