Fast Exact Unlearning for In-Context Learning Data for LLMs
Department of Computer Science, University of Waterloo, Waterloo, Canada（滑铁卢大学计算机科学系）；Department of Computer Science, University of Toronto, Toronto, Canada（多伦多大学计算机科学系）；Vector Institute, Toronto, Canada（向量研究所）
Andrei I. Muresanu, Anvith Thudi, Michael R. Zhang, Nicolas Papernot
Modern machine learning models are expensive to train, and there is a growing concern about the challenge of retroactively removing specific training data. Achieving exact unlearning in deep learning pipelines--producing models as if certain data had never been included in training--remains an open problem. In this paper, we revisit exact unlearning in deep learning and show that for large language models (LLMs) we can efficiently exactly unlearn "fine-tuning data" (the data used to adapt a pre-trained model). This follows from two observations. First, we can use in-context learning to adapt the LLM to the fine-tuning dataset instead of SGD based algorithms. Second, we show that accurate in-context learning can be done with quantized k-means, which allows for effectively constant time unlearning operations. Our evaluation shows that this unlearning recipe has similar performance to fine-tuning alternatives, but vastly reduces the unlearning costs. Our study also highlights the need for new measures of unlearning cost when adapting the learning algorithm to have faster unlearn operations.
Unlearning Isn't Deletion: Investigating Reversibility of Machine Unlearning in LLMs
The Hong Kong Polytechnic University（香港理工大学）；Carnegie Mellon University（卡内基梅隆大学）；University of California, Santa Cruz（加州大学圣克ruz分校）；Huawei Technologies（华为技术有限公司）；Research Centre for Privacy and Security Technologies in Future Smart Systems, PolyU（未来智能系统中的隐私与安全技术研究中心，PolyU）
Data-Free Privacy-Preserving for LLMs via Model Inversion and Selective Unlearning
School of Software Technology, Zhejiang University（浙江大学软件技术学院）；Zhejiang University（浙江大学）；Hefei University of Technology（合肥工业大学）；Institute of Fundamental and Transdisciplinary Research, Zhejiang University（浙江大学基础与交叉学科研究院）；Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security（杭州高新技术区（滨江区）区块链与数据安全研究院）；The State Key Laboratory of Blockchain and Data Security（区块链与数据安全国家重点实验室）；Zhejiang Key Laboratory of Big Data Intelligent Computing（浙江省大数据智能计算重点实验室）
Model Collapse Is Not a Bug but a Feature in Machine Unlearning for LLMs
Dept. of Computer Science & Munich Data Science Institute, Technical University of Munich（计算机科学系及慕尼黑数据科学研究所，技术大学慕尼黑）；Mila, Université de Montréal（蒙特利尔大学Mila）
DP2Unlearning: An Efficient and Guaranteed Unlearning Framework for LLMs
Universitat Rovira i Virgili, Department of Computer Engineering（罗维拉-维格利大学计算机工程系）；Mathematics, CYBERCAT-Center for Cybersecurity Research of Catalonia（数学，加泰罗尼亚网络安全研究中心）
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）
Mitigating Sensitive Information Leakage in LLMs4Code through Machine Unlearning
College of Computer Science and Technology, National University of Defense Technology, Changsha, Hunan, 410073, China（计算机科学与技术学院，国防科技大学，长沙，湖南，410073，中国）；Xichang Satellite Launch Center, Xichang, Sichuan, 615000, China（西昌卫星发射中心，西昌，四川，615000，中国）；Academy of Military Sciences, Beijing, 100091, China（军事科学院，北京，100091，中国）
Operationalising the Right to be Forgotten in LLMs: A Lightweight Sequential Unlearning Framework for Privacy-Aligned Deployment in Politically Sensitive Environments
Department of Mathematics（数学系）；Munster Technological University（穆恩斯特技术大学）；Department of Computer Science（计算机科学系）
Towards Lifecycle Unlearning Commitment Management: Measuring Sample-level Unlearning Completeness
Provable Responsible AI and Data Analytics Lab（可证负责任人工智能与数据 analytics 实验室）；King Abdullah University of Science and Technology（卡塔尔国王 Abdullah 科学与技术大学）；National University of Singapore（新加坡国家大学）；Johns Hopkins University（约翰霍普金斯大学）
本文提出 IAM 框架，通过插值模型在样本上的泛化—拟合差距度量样本级遗忘完整性，可低成本扩展至 LLM，并揭示近似遗忘中过度与不足遗忘风险。
CBD: API-Only LLM Black-Box Unlearning through Controlled Behavioral Divergence
State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications（北京邮电大学网络与交换技术国家重点实验室）；Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing（北京未来区块链与隐私计算高精尖创新中心）；Department of Electronic and Electrical Engineering, Sungkyunkwan University（成均馆大学电子与电气工程系）
Beyond Superficial Unlearning: Sharpness-Aware Robust Erasure of Hallucinations in Multimodal LLMs
College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics（南京航空航天大学计算机科学与技术学院）；Institute for AI, Tsinghua University（清华大学人工智能研究院）；Huzhou University（湖州大学）；Institute of Dataspace, Hefei Comprehensive National Science Center（合肥综合性国家科学中心数据空间研究院）；University of Science and Technology of China（中国科学技术大学）
Unlearning Sensitive Information in Multimodal LLMs: Benchmark and Attack-Defense Evaluation
Department of Computer Science（计算机科学系）；University of North Carolina at Chapel Hill（北卡罗来纳大学 Chapel Hill 分校）；School of Artificial Intelligence and Data Science（人工智能与数据科学学院）；University of Science and Technology of China（中国科学技术大学）
The Frontier of Data Erasure: Machine Unlearning for Large Language Models
Data61, Commonwealth Scientific and Industrial Research Organization（联邦科学与工业研究组织Data61）；School of Systems & Computing, University of New South Wales（新南威尔士大学系统与计算学院）；School of Computer Science, University of Sydney（悉尼大学计算机科学学院）；Faculty of Data Science, City University of Macau（澳门城市大学数据科学学院）；College of Computing & Data Science, Nanyang Technological University（南洋理工大学计算与数据科学学院）
