We introduce a unifying framework that brings two leading "locate-and-edit" model editing techniques -- ROME and MEMIT -- under a single conceptual umbrella, optimizing for the same goal, which we call the preservation-memorization objective. ROME uses an equality constraint to perform one edit at a time, whereas MEMIT employs a more flexible least-square constraint that allows for batched edits. Following the preservation-memorization objective, we present Equality-constrained Mass Model Editing algorithm for Transformers or EMMET, a new batched memory-editing algorithm that uses a closed-form solution for the equality-constrained version of the preservation-memorization objective. EMMET is a batched-version of ROME and is able to perform batched-edits up to a batch-size of 10,000 with very similar performance to MEMIT across multiple dimensions. With EMMET, we unify and achieve symmetry within the "locate-and-edit" algorithms, allowing batched-editing using both objectives.

翻译：我们提出一个统一框架，将两种主流的“定位-编辑”模型编辑技术——ROME和MEMIT——纳入统一概念体系，并优化同一目标（即保存-记忆目标）。ROME采用等式约束实现单次编辑，而MEMIT则使用更灵活的平方最小化约束以支持批量编辑。遵循保存-记忆目标，我们提出基于等式约束的大规模模型编辑算法EMMET（Equality-constrained Mass Model Editing algorithm for Transformers），这是一种利用闭合解实现保存-记忆目标等式约束版本的批量记忆编辑算法。EMMET是ROME的批量版本，能够在批量规模达到10,000时完成编辑，并在多个维度上与MEMIT表现高度一致。通过EMMET，我们统一并实现了“定位-编辑”算法间的对称性，使得两种目标均可用于批量编辑。