Tag: Privacy Protection
All the papers with the tag "Privacy Protection".
OBLIVIATE: Robust and Practical Machine Unlearning for Large Language Models
grok-3-latestScore: 0.74Published: at 13:51OBLIVIATE 提出了一种鲁棒且实用的 LLM 遗忘框架,通过掩码、蒸馏和世界事实损失结合上下文感知遗忘,有效移除目标数据并保持模型性能和流畅性。