通过正负反馈交替优化，让大模型安全遗忘特定知识。
Alternate Preference Optimization for Unlearning Factual Knowledge in Large Language Models
- 用正向反馈补充负向压制，避免模型输出混乱
- 在遗忘知识的同时保持整体性能稳定
- 适合需要隐私保护的模型编辑场景
机器遗忘旨在高效移除特定训练数据（即遗忘集）对大语言模型的影响。然而，现有大模型遗忘方法仅依赖负面反馈来抑制与遗忘集相关的内容，常导致输出荒谬或不一致，降低模型可用性并引发潜在隐私风险。为此，我们提出一种新方法——交替偏好优化（AltPO），结合对遗忘集的负反馈与领域内正反馈。此外，我们引入新的评估指标以衡量遗忘集相关响应的质量。大量实验表明，该方法不仅能有效实现遗忘，还能避免不良模型行为，同时维持整体性能。代码已开源：https://github.com/molereddy/Alternate-Preference-Optimization。
原文摘要 · Abstract (English)
Machine unlearning aims to efficiently eliminate the influence of specific training data, known as the forget set, from the model. However, existing unlearning methods for Large Language Models (LLMs) face a critical challenge: they rely solely on negative feedback to suppress responses related to the forget set, which often results in nonsensical or inconsistent outputs, diminishing model utility and posing potential privacy risks. To address this limitation, we propose a novel approach called Alternate Preference Optimization (AltPO), which combines negative feedback with in-domain positive feedback on the forget set. Additionally, we introduce new evaluation metrics to assess the quality of responses related to the forget set. Extensive experiments show that our approach not only enables effective unlearning but also avoids undesirable model behaviors while maintaining overall model performance. Our implementation can be found at https://github.com/molereddy/Alternate-Preference-Optimization.
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。