针对大语言模型中遗忘的参数任务运算
Per-parameter Task Arithmetic for Unlearning in Large Language Models
AI总结：
PerTA通过参数级调整优化大语言模型的遗忘过程，提升遗忘效果和模型实用性。
摘要：
在大语言模型（LLM）的遗忘过程中，需要移除私人信息。任务运算通过减去特定任务向量（TV）来实现遗忘，该向量定义为在隐私信息调节模型与原始模型之间的参数差异。虽然效率高，但可能导致过度遗忘，因为会破坏保留其他信息所必需的参数。受观察到每个参数在遗忘与保留中的重要性不同的启发，我们提出了一种参数级任务运算（PerTA）机制来重新缩放TV，允许对参数进行调整。这些权重量化了每个参数在遗忘与保留中的相对重要性，通过梯度（即PerTA-grad）或对角线Fisher信息近似（即PerTA-fisher）进行估计。此外，我们讨论了PerTA的有效性，将其扩展为更一般的形式，并提供了进一步的分析。广泛的实验表明，PerTA在标准TV上 consistently 改善，并在许多情况下在遗忘效果和整体模型效用上超过了广泛使用的训练基于遗忘方法。通过保留任务运算的效率同时减轻过度遗忘，PerTA提供了一个原则性和实用的框架用于LLM遗忘。
英文摘要：
In large language model (LLM) unlearning, private information is required to be removed. Task arithmetic unlearns by subtracting a specific task vector (TV)--defined as the parameter difference between a privacy-information-tuned model and the original model. While efficient, it can cause over-forgetting by disrupting parameters essential for retaining other information. Motivated by the observation that each parameter exhibits different importance for forgetting versus retention, we propose a per-parameter task arithmetic (PerTA) mechanism to rescale the TV, allowing per-parameter adjustment. These weights quantify the relative importance of each parameter for forgetting versus retention, estimated via gradients (i.e., PerTA-grad) or the diagonal Fisher information approximation (i.e., PerTA-fisher). Moreover, we discuss the effectiveness of PerTA, extend it to a more general form, and provide further analysis. Extensive experiments demonstrate that PerTA consistently improves upon standard TV, and in many cases surpasses widely used training-based unlearning methods in both forgetting effectiveness and overall model utility. By retaining the efficiency of task arithmetic while mitigating over-forgetting, PerTA offers a principled and practical framework for LLM unlearning.
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。
