Is Bigger Edit Batch Size Always Better? -- An Empirical Study on Model Editing with Llama-3
It addresses a potential limitation in scaling model editing methods for large language models, though it is incremental as it builds on existing techniques.
This study empirically analyzes model editing techniques (ROME, MEMIT, EMMET) on Llama-3, finding that increasing edit batch sizes can degrade performance more than using smaller sequential batches for the same number of edits, with evaluations up to 4096 edits.
This study presents a targeted model editing analysis focused on the latest large language model, Llama-3. We explore the efficacy of popular model editing techniques - ROME, MEMIT, and EMMET, which are designed for precise layer interventions. We identify the most effective layers for targeted edits through an evaluation that encompasses up to 4096 edits across three distinct strategies: sequential editing, batch editing, and a hybrid approach we call as sequential-batch editing. Our findings indicate that increasing edit batch-sizes may degrade model performance more significantly than using smaller edit batches sequentially for equal number of edits. With this, we argue that sequential model editing is an important component for scaling model editing methods and future research should focus on methods that combine both batched and sequential editing. This observation suggests a potential limitation in current model editing methods which push towards bigger edit batch sizes, and we hope it paves way for future investigations into optimizing batch sizes and model editing performance.