提出量化感知遗忘技术，防止低比特量化后模型恢复被删除信息
QUAIL: Quantization Aware Unlearning for Mitigating Misinformation in LLMs
- 通过分析量化阈值发现遗忘更新过小无法生效
- 设计对数空间铰链损失，确保遗忘后输出差异大于量化步长一半
- 适用于需清除敏感信息的4位量化大模型部署场景
机器遗忘旨在不重新训练的情况下从已训练模型中移除特定知识（如版权或隐私数据）。实际部署中模型常被量化至4比特，但我们发现量化会灾难性地恢复被遗忘的信息。本文首先分析低比特量化为何破坏遗忘效果，其次提出一种量化感知遗忘方法。通过计算权重变化统计与量化桶重叠，我们发现典型遗忘更新量太小，无法跨越量化阈值。基于此，引入对数空间铰链损失：对每个遗忘样本，强制未学习模型的输出对数概率与原模型相差至少半个量化步长，确保量化后仍可区分。在语言和分类任务（包括一个推特虚假信息数据集）上评估，本方法在4比特量化下仍能保持遗忘效果，而现有方法几乎完全恢复被遗忘知识。
原文摘要 · Abstract (English)
Machine unlearning aims to remove specific knowledge (e.g., copyrighted or private data) from a trained model without full retraining. In practice, models are often quantized (e.g., 4-bit) for deployment, but we find that quantization can catastrophically restore forgotten information [1]. In this paper, we (1) analyze why low-bit quantization undermines unlearning, and (2) propose a quantization-aware unlearning method to mitigate this. We first compute weight-change statistics and bucket overlaps in quantization to show that typical unlearning updates are too small to cross quantization thresholds. Building on this insight, we introduce a logits space hinge loss: for each forget example, we force the output logits of the unlearned model to differ from the original model by at least a margin (half the quantization step). This ensures forgotten examples remain distinguishable even after quantization. We evaluate on language and classification tasks (including a Twitter misinformation dataset) and show our method preserves forgetting under 4-bit quantization, whereas existing methods almost entirely recover the forgotten knowledge.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。