SOURCE-LINKED INTELLIGENCE

GRACE:Gradient-guided Coreset Selection for LLM Unlearning

arXiv · AI, language, vision and robotics · article · Aug 28, 2026 · UTC

Machine Unlearning methods for Large Language Models typically assume pre-specified forget and retain sets. In realistic settings, however, requests may provide only a few examples of undesired behavior, requiring forget and retain sets to be inferred from heterogeneous corpora. We study this data-selection problem and propose GRACE , a gradient-guided coreset selection method that constructs both forget and retain sets for LLM unlearning. GRACE first computes a forget direction from seed examples that elicit the undesired behavior, then selects a compact forget coreset whose gradients approxi

Read original source ↗ Open in workspace

recordType

paper

region

Global