A Unified Framework for Model Editing
Abstract: 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.
Paper Type: Long
Research Area: Interpretability and Analysis of Models for NLP
Research Area Keywords: knowledge tracing/discovering/inducing, probing
Contribution Types: Model analysis & interpretability, NLP engineering experiment, Approaches low compute settings-efficiency, Publicly available software and/or pre-trained models
Languages Studied: English
Submission Number: 453
Loading