Recent work on model editing using Rank-One Model Editing (ROME), a popular
model editing method, has shown that there are certain facts that the algorithm
is unable to edit without breaking the model. Such edits have previously been
called disabling edits. These disabling edits cause immediate model collapse
and limits the use of ROME for sequential editing. In this paper, we make two
main contributions. Firstly, we show that model collapse with ROME only happens
when making edits using the CounterFact dataset and does not happen when using
the zsRE dataset. Secondly, we find that disabling edits are an artifact of the
original implementation of ROME. With this paper, we provide a more stable
implementation ROME, which we call r-ROME and show that we no longer observe
model collapse when making large scale sequential edits with ROME.

通过对模型编辑中的残疾编辑进行研究，作者发现残疾编辑会导致模型立即崩溃，限制了 Rank-One 模型编辑方法（ROME）的连续编辑的使用。在本文中，作者展示了模型编辑中的崩溃现象只会在使用 CounterFact 数据集进行编辑时出现，而在使用 zsRE 数据集时并不会出现。此外，作者发现残疾编辑是 ROME 原始实现的一个人为问题，通过提供了一个更稳定的 ROME 实现（称为 r-ROME），作者展示了使用 ROME 进行大规模连续编辑时不再观察到模型崩溃的现象。

重建 ROME：解决串行模型编辑中的模型崩溃问题

Rebuilding ROME : Resolving Model Collapse during Sequential Model  Editing

We analyze the storage and recall of factual associations in autoregressive
transformer language models, finding evidence that these associations
correspond to localized, directly-editable computations. We first develop a
causal intervention for identifying neuron activations that are decisive in a
model's factual predictions. This reveals a distinct set of steps in
middle-layer feed-forward modules that mediate factual predictions while
processing subject tokens. To test our hypothesis that these computations
correspond to factual association recall, we modify feed-forward weights to
update specific factual associations using Rank-One Model Editing (ROME). We
find that ROME is effective on a standard zero-shot relation extraction (zsRE)
model-editing task, comparable to existing methods. To perform a more sensitive
evaluation, we also evaluate ROME on a new dataset of counterfactual
assertions, on which it simultaneously maintains both specificity and
generalization, whereas other methods sacrifice one or another. Our results
confirm an important role for mid-layer feed-forward modules in storing factual
associations and suggest that direct manipulation of computational mechanisms
may be a feasible approach for model editing. The code, dataset,
visualizations, and an interactive demo notebook are available at
this https URL

本文使用因果干预技术研究了自回归转换语言模型中实际关联的存储和检索，并发现这些关联对应于本地化的可直接编辑的计算。研究表明中间层前馈模块在存储实际关联方面具有重要作用，并且为模型编辑提供了直接操作计算机制的方法。