用低秩适配器重构梯度，实现高效大模型遗忘。
Recover-to-Forget: Gradient Reconstruction from LoRA for Efficient LLM Unlearning
- 从LoRA更新中重建全模型梯度方向，避免全模型微调。
- 在多个数据集上验证，遗忘效果接近全模型微调但仅需1/10计算量。
- 适用于大模型或黑盒模型，适合需要数据删除的场景。
大模型中的遗忘机制对动态知识更新、数据删除权执行和模型行为修正至关重要。然而，现有方法通常需要全模型微调或原始训练数据，限制了可扩展性和实用性。本文提出一种名为 Recover-to-Forget (R2F) 的新框架，基于从低秩 LoRA 适配器更新中重构全模型梯度方向，实现高效遗忘。不通过全模型反向传播，而是利用多组改写提示计算 LoRA 参数梯度，并训练一个梯度解码器以逼近对应全模型梯度。为确保在更大或黑盒模型上的适用性，解码器在代理模型上训练后迁移到目标模型。我们提供了跨模型泛化的理论分析，并证明该方法能在保持模型通用性能的同时有效实现遗忘。实验表明，R2F 在无需全重训或内部参数访问的情况下，提供了一种可扩展且轻量级的大模型遗忘方案。
原文摘要 · Abstract (English)
Unlearning in large foundation models (e.g., LLMs) is essential for enabling dynamic knowledge updates, enforcing data deletion rights, and correcting model behavior. However, existing unlearning methods often require full-model fine-tuning or access to the original training data, which limits their scalability and practicality. In this work, we introduce Recover-to-Forget (R2F), a novel framework for efficient unlearning in LLMs based on reconstructing full-model gradient directions from low-rank LoRA adapter updates. Rather than performing backpropagation through the full model, we compute gradients with respect to LoRA parameters using multiple paraphrased prompts and train a gradient decoder to approximate the corresponding full-model gradients. To ensure applicability to larger or black-box models, the decoder is trained on a proxy model and transferred to target models. We provide a theoretical analysis of cross-model generalization and demonstrate that our method achieves effective unlearning while preserving general model performance. Experimental results demonstrate that R2F offers a scalable and lightweight alternative for unlearning in pretrained LLMs without requiring full retraining or access to internal parameters.
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。