English
Related papers

Related papers: Toward Understanding Unlearning Difficulty: A Mech…

200 papers

Generative AI technologies have been deployed in many places, such as (multimodal) large language models and vision generative models. Their remarkable performance should be attributed to massive training data and emergent reasoning…

Machine Learning · Computer Science 2024-07-31 Zheyuan Liu , Guangyao Dou , Zhaoxuan Tan , Yijun Tian , Meng Jiang

Testing of deep learning models is challenging due to the excessive number and complexity of computations involved. As a result, test data selection is performed manually and in an ad hoc way. This raises the question of how we can…

Machine Learning · Computer Science 2019-05-01 Wei Ma , Mike Papadakis , Anestis Tsakmalis , Maxime Cordy , Yves Le Traon

Effective adaptation to distribution shifts in training data is pivotal for sustaining robustness in neural networks, especially when removing specific biases or outdated information, a process known as machine unlearning. Traditional…

Machine Learning · Computer Science 2024-05-24 Ling Han , Hao Huang , Dustin Scheinost , Mary-Anne Hartley , María Rodríguez Martínez

Current LLM unlearning methods are not robust. A few steps of finetuning can revert their effects. We begin by showing that this is true even for an idealized form of unlearning: training to imitate a model that was never trained on…

Large Language Models (LLMs) demonstrate remarkable capabilities, but their training on massive corpora poses significant risks from memorized sensitive information. To mitigate these issues and align with legal standards, unlearning has…

Computation and Language · Computer Science 2025-11-18 Ruichen Qiu , Jiajun Tan , Jiayue Pu , Honglin Wang , Xiao-Shan Gao , Fei Sun

Understanding uncertainty plays a critical role in achieving common ground (Clark et al.,1983). This is especially important for multimodal AI systems that collaborate with users to solve a problem or guide the user through a challenging…

Computation and Language · Computer Science 2024-10-21 Qi Cheng , Mert İnan , Rahma Mbarki , Grace Grmek , Theresa Choi , Yiming Sun , Kimele Persaud , Jenny Wang , Malihe Alikhani

The right to be forgotten mandates that machine learning models enable the erasure of a data owner's data and information from a trained model. Removing data from the dataset alone is inadequate, as machine learning models can memorize…

Machine Learning · Computer Science 2024-10-16 Xiaoyu Xia , Ziqi Wang , Ruoxi Sun , Bowen Liu , Ibrahim Khalil , Minhui Xue

Machine unlearning aims to selectively remove targeted knowledge from Large Language Models (LLMs), ensuring they forget specified content while retaining essential information. Existing unlearning metrics assess whether a model correctly…

Computation and Language · Computer Science 2025-05-28 Wonje Jeung , Sangyeon Yoon , Albert No

Unlearning in large language models (LLMs) aims to remove specified data, but its efficacy is typically assessed with task-level metrics like accuracy and perplexity. We show that these metrics can be misleading, as models can appear to…

Computation and Language · Computer Science 2026-05-19 Xiaoyu Xu , Xiang Yue , Yang Liu , Qingqing Ye , Huadi Zheng , Peizhao Hu , Minxin Du , Haibo Hu

Machine unlearning offers a promising solution to privacy and safety concerns in large language models (LLMs) by selectively removing targeted knowledge while preserving utility. However, current methods are highly sensitive to downstream…

Pretrained language models memorize vast amounts of information, including private and copyrighted data, raising significant safety concerns. Retraining these models after excluding sensitive data is prohibitively expensive, making machine…

Computation and Language · Computer Science 2024-10-04 Minseok Choi , Kyunghyun Min , Jaegul Choo

Curriculum learning (CL) describes a machine learning training strategy in which samples are gradually introduced into the training process based on their difficulty. Despite a partially contradictory body of evidence in the literature, CL…

Machine Learning · Computer Science 2024-11-05 Simon Rampp , Manuel Milling , Andreas Triantafyllopoulos , Björn W. Schuller

Current unlearning metrics for generative models evaluate success based on reference responses or classifier outputs rather than assessing the core objective: whether the unlearned model behaves indistinguishably from a model that never saw…

Machine Learning · Computer Science 2025-10-16 Sungjun Cho , Dasol Hwang , Frederic Sala , Sangheum Hwang , Kyunghyun Cho , Sungmin Cha

Machine unlearning has emerged as a prevalent technical solution for selectively removing unwanted knowledge absorbed during pre-training, without requiring full retraining. While recent unlearning techniques can effectively remove…

Machine Learning · Computer Science 2025-11-04 Myeongseob Ko , Hoang Anh Just , Charles Fleming , Ming Jin , Ruoxi Jia

While Large Language Models (LLMs) excel at code generation, their inherent tendency toward verbatim memorization of training data introduces critical risks like copyright infringement, insecure emission, and deprecated API utilization,…

Software Engineering · Computer Science 2025-11-25 Xue Jiang , Yihong Dong , Huangzhao Zhang , Tangxinyu Wang , Zheng Fang , Yingwei Ma , Rongyu Cao , Binhua Li , Zhi Jin , Wenpin Jiao , Yongbin Li , Ge Li

Machine unlearning is the task of updating machine learning (ML) models after a subset of the training data they were trained on is deleted. Methods for the task are desired to combine effectiveness and efficiency, i.e., they should…

Machine Learning · Computer Science 2021-08-17 Ananth Mahadevan , Michael Mathioudakis

Recent work has demonstrated that machine unlearning in Large Language Models (LLMs) fails to generalize across languages: knowledge erased in one language frequently remains accessible through others. However, the underlying cause of this…

Cryptography and Security · Computer Science 2026-02-27 Taoran Li , Varun Chandrasekaran , Zhiyuan Yu

Recently machine unlearning (MU) is proposed to remove the imprints of revoked samples from the already trained model parameters, to solve users' privacy concern. Different from the runtime expensive retraining from scratch, there exist two…

Machine Learning · Computer Science 2024-12-20 Mingxin Li , Yizhen Yu , Ning Wang , Zhigang Wang , Xiaodong Wang , Haipeng Qu , Jia Xu , Shen Su , Zhichao Yin

Pre-trained language models have achieved remarkable success across diverse applications but remain susceptible to spurious, concept-driven correlations that impair robustness and fairness. In this work, we introduce CURE, a novel and…

Computation and Language · Computer Science 2025-09-11 Aysenur Kocak , Shuo Yang , Bardh Prenkaj , Gjergji Kasneci

Machine unlearning is the process of removing the impact of a particular set of training samples from a pretrained model. It aims to fulfill the "right to be forgotten", which grants the individuals such as patients the right to reconsider…

Machine Learning · Computer Science 2024-07-11 Reza Nasirigerdeh , Nader Razmi , Julia A. Schnabel , Daniel Rueckert , Georgios Kaissis