The rapid advancement of Large Language Models (LLMs) has demonstrated their vast potential across various domains, attributed to their extensive pretraining knowledge and exceptional generalizability. However, LLMs often encounter challenges in generating harmful content when faced with problematic prompts. To address this problem, existing work attempted to implement a gradient ascent based approach to prevent LLMs from producing harmful output. While these methods can be effective, they frequently impact the model utility in responding to normal prompts. To address this gap, we introduce Selective Knowledge negation Unlearning (SKU), a novel unlearning framework for LLMs, designed to eliminate harmful knowledge while preserving utility on normal prompts. Specifically, SKU is consisted of two stages: harmful knowledge acquisition stage and knowledge negation stage. The first stage aims to identify and acquire harmful knowledge within the model, whereas the second is dedicated to remove this knowledge. SKU selectively isolates and removes harmful knowledge in model parameters, ensuring the model's performance remains robust on normal prompts. Our experiments conducted across various LLM architectures demonstrate that SKU identifies a good balance point between removing harmful information and preserving utility.
A Comprehensive Survey of Machine Unlearning Techniques for Large Language Models
Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)(莫扎德大学人工智能学院);Fraunhofer Institute for Open Communication Systems (FOKUS)(弗劳恩霍夫开放通信系统研究所);Technical University of Munich(慕尼黑技术大学);Technical University of Darmstadt(达姆施塔特技术大学);University of Toronto(多伦多大学)
Rethinking Machine Unlearning for Large Language Models
Michigan State University(密歇根州立大学);IBM Research(IBM研究院);University of North Carolina at Chapel Hill(北卡罗来纳大学教堂山分校);University of California, Santa Cruz(加州大学圣克鲁兹分校);ByteDance Research(字节跳动研究院);Stanford University(斯坦福大学)
Machine Unlearning of Pre-trained Large Language Models
University of Virginia(弗吉尼亚大学);Georgia Institute of Technology(佐治亚理工学院);The Hong Kong Polytechnic University(香港理工大学);University of Melbourne(墨尔本大学);Carnegie Mellon University(卡内基梅隆大学)
Machine Unlearning Meets Adversarial Robustness via Constrained Interventions on LLMs
Department of Computer Science, Université Paris-Dauphine(巴黎-索邦大学计算机科学系);Institute of Mathematics, EPFL(苏黎世联邦理工学院数学研究所);Computational Engineering Lab, Empa(Empa计算工程实验室)
KGA: A General Machine Unlearning Framework Based on Knowledge Gap Alignment
The Chinese University of Hong Kong(香港中文大学);MoE Key Laboratory of High Confidence Software Technologies(教育部高可信软件技术重点实验室);The University of Queensland(昆士兰大学)
Machine Unlearning in Hyperbolic vs. Euclidean Multimodal Contrastive Learning: Adapting Alignment Calibration to MERU
Aalborg University(奥尔堡大学);University of Barcelona(巴塞罗那大学);Computer Vision Center(计算机视觉中心);Milestone Systems(里程碑系统公司);Pioneer Center for Artificial Intelligence(先锋人工智能中心)