Machine Unlearning of Pre-trained Large Language Models

arXiv:2402.15159v1 Announce Type: cross
Abstract: This study investigates the concept of the `right to be forgotten' within the context of large language models (LLMs). We explore machine unlearning as a pivotal solution, with a focus on pre-trained models--a notably under-researched area. Our research delineates a comprehensive framework for machine unlearning in pre-trained LLMs, encompassing a critical analysis of seven diverse unlearning methods. Through rigorous evaluation using curated datasets from arXiv, books, and GitHub, we establish a robust benchmark for unlearning …

area arxiv concept context cs.ai cs.cl cs.cr cs.lg focus framework language language models large llms machine research right to be forgotten solution study under