Is Bigger Edit Batch Size Always Better? -- An Empirical Study on Model Editing with Llama-3

arXiv:2405.00664v1 Announce Type: cross
Abstract: 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 …

abstract analysis arxiv bigger cs.ai cs.cl cs.lg edit editing explore identify language language model large language large language model latest layer llama popular study type