用自生成数据迭代训练，让大模型学会遗忘敏感信息。
Reveal and Release: Iterative LLM Unlearning with Self-generated Data
- 通过优化指令让模型自曝记忆内容，生成遗忘数据。
- 迭代调整参数，实现遗忘效果与保留能力的平衡。
- 适合需要保护隐私或合规的模型更新场景。
大语言模型的遗忘技术已证明能有效消除不良数据的影响。现有方法通常假设可完全访问遗忘数据集，但面临两大挑战：（1）遗忘数据常涉及隐私、稀有或受法律监管，获取成本高或不现实；（2）可用遗忘数据的分布可能与模型内部表征不一致。为此，我们提出「揭示与释放」方法，利用自生成数据进行遗忘学习。通过优化提示引导模型揭示其知识，再以自生成数据为依据，采用基于参数高效模块的迭代遗忘框架，在权重空间中逐步调整模型。实验表明，该方法在遗忘质量与功能保留之间取得了良好平衡。
原文摘要 · Abstract (English)
Large language model (LLM) unlearning has demonstrated effectiveness in removing the influence of undesirable data (also known as forget data). Existing approaches typically assume full access to the forget dataset, overlooking two key challenges: (1) Forget data is often privacy-sensitive, rare, or legally regulated, making it expensive or impractical to obtain (2) The distribution of available forget data may not align with how that information is represented within the model. To address these limitations, we propose a ``Reveal-and-Release'' method to unlearn with self-generated data, where we prompt the model to reveal what it knows using optimized instructions. To fully utilize the self-generated forget data, we propose an iterative unlearning framework, where we make incremental adjustments to the model's weight space with parameter-efficient modules trained on the forget data. Experimental results demonstrate that our method balances the tradeoff between forget quality and utility preservation.
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。