Unveiling Entity-Level Unlearning for Large Language Models: A Comprehensive Analysis

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Ma, Weitao, Feng, Xiaocheng, Zhong, Weihong, Huang, Lei, Ye, Yangfan, Feng, Xiachong, Qin, Bing
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913846088695808
author Ma, Weitao
Feng, Xiaocheng
Zhong, Weihong
Huang, Lei
Ye, Yangfan
Feng, Xiachong
Qin, Bing
author_facet Ma, Weitao
Feng, Xiaocheng
Zhong, Weihong
Huang, Lei
Ye, Yangfan
Feng, Xiachong
Qin, Bing
contents Large language model unlearning has garnered increasing attention due to its potential to address security and privacy concerns, leading to extensive research in the field. However, much of this research has concentrated on instance-level unlearning, specifically targeting the removal of predefined instances containing sensitive content. This focus has left a significant gap in the exploration of full entity-level unlearning, which is critical in real-world scenarios such as copyright protection. To this end, we propose a novel task of Entity-level unlearning, which aims to erase entity-related knowledge from the target model completely. To thoroughly investigate this task, we systematically evaluate trending unlearning algorithms, revealing that current methods struggle to achieve effective entity-level unlearning. Then, we further explore the factors that influence the performance of the unlearning algorithms, identifying that knowledge coverage and the size of the forget set play pivotal roles. Notably, our analysis also uncovers that entities introduced through fine-tuning are more vulnerable to unlearning than pre-trained entities. These findings collectively offer valuable insights for advancing entity-level unlearning for LLMs.
format Preprint
id arxiv_https___arxiv_org_abs_2406_15796
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Unveiling Entity-Level Unlearning for Large Language Models: A Comprehensive Analysis
Ma, Weitao
Feng, Xiaocheng
Zhong, Weihong
Huang, Lei
Ye, Yangfan
Feng, Xiachong
Qin, Bing
Computation and Language
Large language model unlearning has garnered increasing attention due to its potential to address security and privacy concerns, leading to extensive research in the field. However, much of this research has concentrated on instance-level unlearning, specifically targeting the removal of predefined instances containing sensitive content. This focus has left a significant gap in the exploration of full entity-level unlearning, which is critical in real-world scenarios such as copyright protection. To this end, we propose a novel task of Entity-level unlearning, which aims to erase entity-related knowledge from the target model completely. To thoroughly investigate this task, we systematically evaluate trending unlearning algorithms, revealing that current methods struggle to achieve effective entity-level unlearning. Then, we further explore the factors that influence the performance of the unlearning algorithms, identifying that knowledge coverage and the size of the forget set play pivotal roles. Notably, our analysis also uncovers that entities introduced through fine-tuning are more vulnerable to unlearning than pre-trained entities. These findings collectively offer valuable insights for advancing entity-level unlearning for LLMs.
title Unveiling Entity-Level Unlearning for Large Language Models: A Comprehensive Analysis
topic Computation and Language
url https://arxiv.org/abs/2406.15796