Abstract
The advent of Large Language Models (LLMs) has revolutionized natural language processing, enabling advanced understanding and reasoning capabilities across a variety of tasks. Fine-tuning these models for specific domains, particularly through Parameter-Efficient Fine-Tuning (PEFT) strategies like LoRA, has become a prevalent practice due to its efficiency. However, this raises significant privacy and security concerns, as models may inadvertently retain and disseminate sensitive or undesirable information. To address these issues, we introduce a novel instance-wise unlearning framework, LLMEraser, which systematically categorizes unlearning tasks and applies precise parameter adjustments using influence functions. Unlike traditional unlearning techniques that are often limited in scope and require extensive retraining, LLMEraser is designed to handle a broad spectrum of unlearning tasks without compromising model performance. Extensive experiments on benchmark datasets demonstrate that LLMEraser excels in efficiently managing various unlearning scenarios while maintaining the overall integrity and efficacy of the models.
Citation:
@article{DiffGAD,
author = {Jinghan Li and
Yuan Gao and
Jinda Lu and
Junfeng Fang and
Congcong Wen and
Hui Lin and
Xiang Wang},
title = {DiffGAD: {A} Diffusion-based Unsupervised Graph Anomaly Detector},
journal = {CoRR},
volume = {abs/2410.06549},
year = {2024}
}
Chenlu Ding
丁陈璐
Jiancan Wu
吴剑灿 副研究员
Jinda Lu
卢金达
Xiang Wang
王翔 教授
