SOURCE-LINKED INTELLIGENCE

Graph-Guided Selective Unlearning for Language Models: Controlling Support Routes Beyond Forget Seeds

arXiv · AI, language, vision and robotics · article · Aug 27, 2026 · UTC

Enterprises fine-tune language models on proprietary data that may later require removal due to privacy, contractual, or compliance obligations. Selective unlearning removes requested knowledge while preserving model utility, offering a practical alternative to full retraining, but existing methods treat the explicitly identified forget examples as the complete deletion scope. This is insufficient when target knowledge remains recoverable through paraphrases, aliases, or neighboring training examples. We propose GRAPHSU, a graph-guided controller that expands the deletion scope beyond forget s

Read original source ↗ Open in workspace

recordType

paper

region

Global