超越表面遗忘：通过知识密度估计和块重新插入实现彻底遗忘
Beyond Superficial Forgetting: Thorough Unlearning through Knowledge Density Estimation and Block Re-insertion
AI总结：
KUnBR通过知识密度估计和块重新插入策略，有效解决大语言模型中有害知识的彻底移除问题，实现高效的遗忘与模型实用性平衡。
摘要：
机器遗忘，即在不从头重新训练的情况下，有选择地从预训练模型中移除有害知识，对于解决大语言模型（LLMs）中的隐私、合规性和伦理问题至关重要。然而，现有遗忘方法往往难以彻底移除有害知识，导致残留的有害知识容易被恢复。为了解决这些限制，我们提出了基于块重新插入的知识密度引导遗忘（KUnBR），一种新的方法，首先识别包含丰富有害知识的层，然后通过重新插入策略彻底消除有害知识。我们的方法引入了知识密度估计来量化和定位包含最多有害知识的层，从而实现精确遗忘。此外，我们设计了一种层重新插入策略，将包含大量有害知识的层提取并重新插入到原始LLM中，绕过覆盖层造成的梯度阻碍，确保在遗忘过程中有效传播梯度。在多个遗忘和通用能力基准上的广泛实验表明，KUnBR在保持模型实用性的同时实现了最先进的遗忘性能。
英文摘要：
Machine unlearning, which selectively removes harmful knowledge from a pre-trained model without retraining from scratch, is crucial for addressing privacy, regulatory compliance, and ethical concerns in Large Language Models (LLMs). However, existing unlearning methods often struggle to thoroughly remove harmful knowledge, leaving residual harmful knowledge that can be easily recovered. To address these limitations, we propose Knowledge Density-Guided Unlearning via Blocks Reinsertion (KUnBR), a novel approach that first identifies layers with rich harmful knowledge and then thoroughly eliminates the harmful knowledge via re-insertion strategy. Our method introduces knowledge density estimation to quantify and locate layers containing the most harmful knowledge, enabling precise unlearning. Additionally, we design a layer re-insertion strategy that extracts and re-inserts harmful knowledge-rich layers into the original LLM, bypassing gradient obstruction caused by cover layers and ensuring effective gradient propagation during unlearning. Extensive experiments conducted on several unlearning and general capability benchmarks demonstrate that KUnBR achieves state-of-the-art forgetting performance while maintaining model utility.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
