AINeutralarXiv – CS AI · 9h ago6/10
🧠
SHRED: Retain-Set-Free Unlearning via Self-Distillation with Logit Demotion
Researchers introduce SHRED, a machine unlearning method for large language models that removes memorized private or copyrighted data without requiring a curated retain set of examples. By selectively demoting logits of high-information tokens while preserving model utility through self-distillation, SHRED achieves superior trade-offs between forgetting efficacy and performance compared to existing retain-set-dependent approaches.