English
Related papers

Related papers: Robust LLM Unlearning with MUDMAN: Meta-Unlearning…

200 papers

Representation Misdirection for Unlearning (RMU), which steers model representation in the intermediate layer to a target random representation, is an effective method for large language model (LLM) unlearning. Despite its high performance,…

Computation and Language · Computer Science 2025-02-07 Dang Huu-Tien , Trung-Tin Pham , Hoang Thanh-Tung , Naoya Inoue

Large language models (LLMs) inherently absorb harmful knowledge, misinformation, and personal data during pretraining on large-scale web corpora, with no native mechanism for selective removal. While machine unlearning offers a principled…

Artificial Intelligence · Computer Science 2026-04-15 Jagadeesh Rachapudi , Pranav Singh , Ritali Vatsi , Praful Hambarde , Amit Shukla

The widespread deployment of Large Language Models (LLMs) trained on massive, uncurated corpora has raised growing concerns about the inclusion of sensitive, copyrighted, or illegal content. This has led to increasing interest in LLM…

Computation and Language · Computer Science 2025-06-10 Chenlong Zhang , Zhuoran Jin , Hongbang Yuan , Jiaheng Wei , Tong Zhou , Kang Liu , Jun Zhao , Yubo Chen

Fine-tuning-as-a-service, while commercially successful for Large Language Model (LLM) providers, exposes models to harmful fine-tuning attacks. As a widely explored defense paradigm against such attacks, unlearning attempts to remove…

Cryptography and Security · Computer Science 2025-05-23 Biao Yi , Tiansheng Huang , Baolei Zhang , Tong Li , Lihai Nie , Zheli Liu , Li Shen

Language models trained on web-scale corpora risk memorizing and exposing sensitive information, prompting the need for effective machine unlearning. Prior methods mainly focus on input queries to suppress sensitive outputs, yet this often…

Artificial Intelligence · Computer Science 2025-10-01 Junbeom Kim , Kyuyoung Kim , Jihoon Tack , Dongha Lim , Jinwoo Shin

This paper investigates the propagation of harmful information in multilingual large language models (LLMs) and evaluates the efficacy of various unlearning methods. We demonstrate that fake information, regardless of the language it is in,…

Computation and Language · Computer Science 2025-09-04 Taiming Lu , Philipp Koehn

The ability to selectively remove knowledge from LLMs is highly desirable. However, existing methods often struggle with balancing unlearning efficacy and retain model utility, and lack controllability at inference time to emulate base…

Machine Learning · Computer Science 2025-10-09 William F. Shen , Xinchi Qiu , Meghdad Kurmanji , Alex Iacob , Lorenzo Sani , Yihong Chen , Nicola Cancedda , Nicholas D. Lane

Deep machine unlearning is the problem of `removing' from a trained neural network a subset of its training set. This problem is very timely and has many applications, including the key tasks of removing biases (RB), resolving confusion…

Machine Learning · Computer Science 2023-10-31 Meghdad Kurmanji , Peter Triantafillou , Jamie Hayes , Eleni Triantafillou

Large Language Models (LLMs) unlearning is crucial for removing hazardous or privacy-leaking information from the model. Practical LLM unlearning demands satisfying multiple challenging objectives simultaneously: removing undesirable…

Machine Learning · Computer Science 2026-04-20 Yisheng Zhong , Sijia Liu , Zhuangdi Zhu

Multimodal contrastive learning has emerged as a powerful paradigm for building high-quality features using the complementary strengths of various data modalities. However, the open nature of such systems inadvertently increases the…

Computer Vision and Pattern Recognition · Computer Science 2024-03-26 Siyuan Liang , Kuanrong Liu , Jiajun Gong , Jiawei Liang , Yuan Xun , Ee-Chien Chang , Xiaochun Cao

Machine Unlearning (MU) has emerged as a promising approach to addressing persistent challenges in Machine Learning (ML) systems. By enabling the selective removal of learned data, MU introduces protective, corrective, and adaptive…

Computers and Society · Computer Science 2025-11-13 Betty Mayeku , Sandra Hummel , Parisa Memarmoshrefi

Pre-trained Large Language Models (LLMs) have demonstrated remarkable capabilities but also pose risks by learning and generating copyrighted material, leading to significant legal and ethical concerns. In a potential real-world scenario,…

Computation and Language · Computer Science 2025-02-12 Guangyao Dou

Machine unlearning methods aim to remove sensitive or unwanted content from trained models, but typically demand extensive model updates at significant computational cost while potentially degrading model performance on both related and…

Machine Learning · Computer Science 2025-06-02 Zikui Cai , Yaoteng Tan , M. Salman Asif

Large language models are powerful but costly. We ask whether meta-learning can make the pretraining of small language models not only better but also more interpretable. We integrate first-order MAML with subset-masked LM pretraining,…

Computation and Language · Computer Science 2025-11-10 David Demitri Africa , Yuval Weiss , Paula Buttery , Richard Diehl Martinez

Large language models (LLMs) can internalize private or harmful content, motivating unlearning that removes a forget set while preserving retaining knowledge. However, forgetting updates often cause collateral degradation on retaining…

Machine Learning · Computer Science 2026-02-03 Duo Zhou , Yuji Zhang , Tianxin Wei , Ruizhong Qiu , Ke Yang , Xiao Lin , Cheng Qian , Jingrui He , Hanghang Tong , Chengxiang Zhai , Heng Ji , Huan Zhang

Jailbreak attacks pose a serious threat to the safety of Large Language Models (LLMs) by crafting adversarial prompts that bypass alignment mechanisms, causing the models to produce harmful, restricted, or biased content. In this paper, we…

Machine Learning · Computer Science 2025-08-22 Xiangman Li , Xiaodong Wu , Qi Li , Jianbing Ni , Rongxing Lu

Text-to-image (T2I) diffusion models have achieved impressive image generation quality and are increasingly fine-tuned for personalized applications. However, these models often inherit unsafe behaviors from toxic pretraining data, raising…

Machine Learning · Computer Science 2025-12-09 Boheng Li , Renjie Gu , Junjie Wang , Leyi Qi , Yiming Li , Run Wang , Zhan Qin , Tianwei Zhang

Visual modality is the most vulnerable to privacy leakage in real-world multimodal applications like autonomous driving with visual and radar data; Machine unlearning removes specific training data from pre-trained models to address privacy…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Jinghan Xu Yuyang Zhang Qixuan Cai Jiancheng Chen Keqiu Li

Machine unlearning in foundation models (e.g., language and vision transformers) is essential for privacy and safety; however, existing approaches are unstable and unreliable. A widely used strategy, the gradient difference method, applies…

Machine Learning · Computer Science 2026-03-19 Arpit Garg , Hemanth Saratchandran , Ravi Garg , Simon Lucey

Machine unlearning (MUL) refers to the problem of making a pre-trained model selectively forget some training instances or class(es) while retaining performance on the remaining dataset. Existing MUL research involves fine-tuning using a…

Computer Vision and Pattern Recognition · Computer Science 2025-07-08 Soumya Roy , Soumya Banerjee , Vinay Verma , Soumik Dasgupta , Deepak Gupta , Piyush Rai