AI RESEARCH
Downgrade to Upgrade: Optimizer Simplification Enhances Robustness in LLM Unlearning
arXiv CS.LG
•
ArXi:2510.00761v5 Announce Type: replace Large language model (LLM) unlearning aims to surgically remove the influence of undesired data or knowledge from an existing model while preserving its utility on unrelated tasks. This paradigm has shown promise in addressing privacy and safety concerns. However, recent findings reveal that unlearning effects are often fragile: post-unlearning manipulations such as weight quantization or fine-tuning can quickly neutralize the intended forgetting.