面向通过纠缠引导与代理约束缓解大语言模型卸载过度遗忘的方案
Towards Mitigating Excessive Forgetting in LLM Unlearning via Entanglement-Guidance with Proxy Constraint
AI总结：
EGUP通过纠缠引导与代理约束缓解大语言模型卸载过度遗忘问题，提升卸载-效用权衡性能。
摘要：
大型语言模型（LLMs）是在包含私人或受版权保护内容的大量数据集上进行训练的。由于隐私和所有权问题日益增长，数据所有者可能会要求从训练模型中移除他们的数据。机器卸载提供了一种实用的解决方案，可以在不完全重新训练的情况下移除特定数据的影响。然而，大多数现有方法仍然面临过度卸载的问题，因为缺乏一个原则性的机制来调节遗忘边界，导致不必要的效用降级和隐私和稳健性风险的增加。在本工作中，我们提出了EGUP（通过代理约束的纠缠引导卸载），这是一种新颖的框架，利用纠缠和代理约束来引导卸载过程，同时缓解过度卸载。在每个迭代中，EGUP利用跨样本纠缠来自适应重新加权卸载强度，将更多的卸载努力分配给与保留知识语义更接近的遗忘样本。在多个迭代中，EGUP利用内样本纠缠来跟踪每个遗忘样本的表示转移，并动态调整其卸载努力。此外，我们引入了代理约束，该约束近似了卸载后模型的预期输出，形成一个参考边界，从而软性规范卸载过程。EGUP与现有的基于梯度的目标兼容，并且作为可插拔的增强方案。我们评估了EGUP在TOFU和MUSE基准上的表现，证明了在多个LLM上卸载效用权衡方面的持续改进。此外，EGUP在性能接近重新训练模型的同时，保持了可扩展性和稳健性。
英文摘要：
Large language models (LLMs) are trained on massive datasets that may include private or copyrighted content. Due to growing privacy and ownership concerns, data owners may request the removal of their data from trained models. Machine unlearning provides a practical solution by removing the influence of specific data without full retraining. However, most existing methods still suffer from over-unlearning due to the lack of a principled mechanism to regulate the forgetting boundary, leading to unnecessary utility degradation and heightened privacy and robustness risks. In this work, we propose EGUP (Entanglement-Guided Unlearning with Proxy Constraint), a novel framework that leverages entanglement and proxy constraint to guide the unlearning process while mitigating over-unlearning. Within each iteration, EGUP employs inter-sample entanglement to adaptively reweight the unlearning strength, assigning greater unlearning efforts to forget samples that are semantically closer to retained knowledge. Across iterations, EGUP leverages intra-sample entanglement to track the representation shift of each forget sample and dynamically adjust its unlearning effort. In addition, we incorporate a proxy constraint that approximates the model's expected outputs after unlearning, forming a reference boundary that softly regularizes the unlearning process. EGUP is compatible with existing gradient-based objectives and serves as a plug-and-play enhancement. We evaluate EGUP on the TOFU and MUSE benchmarks, demonstrating consistent improvements in the unlearning-utility trade-off across multiple LLMs. Moreover, EGUP achieves performance close to the retrained model while remaining scalable and robust.
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。
