English
Related papers

Related papers: GUARD: Generation-time LLM Unlearning via Adaptive…

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

Machine unlearning -- efficiently removing the effect of a small "forget set" of training data on a pre-trained machine learning model -- has recently attracted significant research interest. Despite this interest, however, recent work…

Machine Learning · Computer Science 2024-11-13 Kristian Georgiev , Roy Rinberg , Sung Min Park , Shivam Garg , Andrew Ilyas , Aleksander Madry , Seth Neel

LLM unlearning is a technique to remove the impacts of undesirable knowledge from the model without retraining from scratch, which is indispensable towards trustworthy AI. Existing unlearning methods face significant limitations:…

Machine Learning · Computer Science 2026-03-02 Yisheng Zhong , Zhengbang Yang , Zhuangdi Zhu

Knowledge retrieval with multi-modal queries plays a crucial role in supporting knowledge-intensive multi-modal applications. However, existing methods face challenges in terms of their effectiveness and training efficiency, especially when…

Information Retrieval · Computer Science 2024-01-17 Xinwei Long , Jiali Zeng , Fandong Meng , Zhiyuan Ma , Kaiyan Zhang , Bowen Zhou , Jie Zhou

Large language models (LLMs) have achieved remarkable success across natural language processing tasks, yet their widespread deployment raises pressing concerns around privacy, copyright, security, and bias. Machine unlearning has emerged…

Computation and Language · Computer Science 2026-01-21 Tyler Lizzo , Larry Heck

Fine-tuning-based unlearning methods prevail for preventing targeted harmful, sensitive, or copyrighted information within large language models while preserving overall capabilities. However, the true effectiveness of these methods is…

Computation and Language · Computer Science 2024-10-16 Yihuai Hong , Yuelin Zou , Lijie Hu , Ziqian Zeng , Di Wang , Haiqin Yang

As large language models (LLMs) are increasingly used across various applications, there is a growing need to control text generation to satisfy specific constraints or requirements. This raises a crucial question: Is it possible to…

Computation and Language · Computer Science 2025-07-03 Minbeom Kim , Thibaut Thonet , Jos Rozen , Hwaran Lee , Kyomin Jung , Marc Dymetman

Foundation models have transformed multimedia analysis by enabling robust and transferable representations across diverse modalities and tasks. However, their static deployment conflicts with growing societal and regulatory demands --…

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

Large language models (LLMs) have advanced to encompass extensive knowledge across diverse domains. Yet controlling what a large language model should not know is important for ensuring alignment and thus safe use. However, accurately and…

Computation and Language · Computer Science 2024-11-01 Chris Yuhao Liu , Yaxuan Wang , Jeffrey Flanigan , Yang Liu

Multimodal Large Language Models (MLLMs) achieve remarkable capabilities but can inadvertently memorize privacy-sensitive information. Although existing unlearning methods can remove such knowledge, they fail to achieve benign forgetting…

Artificial Intelligence · Computer Science 2025-11-26 Zhen Zeng , Leijiang Gu , Zhangling Duan , Feng Li , Zenglin Shi , Cees G. M. Snoek , Meng Wang

Large language models (LLMs) risk retaining unauthorized or sensitive information from their training data, which raises privacy concerns. LLM unlearning seeks to mitigate these risks by selectively removing specified data while maintaining…

Computation and Language · Computer Science 2025-05-29 Hwan Chang , Hwanhee Lee

Retrieval-augmented generation (RAG) has emerged as a promising solution for mitigating hallucinations of large language models (LLMs) with retrieved external knowledge. Adaptive RAG enhances this approach by enabling dynamic retrieval…

Computation and Language · Computer Science 2024-10-07 Huanshuo Liu , Hao Zhang , Zhijiang Guo , Jing Wang , Kuicai Dong , Xiangyang Li , Yi Quan Lee , Cong Zhang , Yong Liu

Large language model (LLM) unlearning aims to remove specific data influences from pre-trained model without costly retraining, addressing privacy, copyright, and safety concerns. However, recent studies reveal a critical vulnerability:…

Computation and Language · Computer Science 2026-05-13 Zeguan Xiao , Xuanzhe Xu , Yun Chen , Yong Wang , Jian Yang , Yanqing Hu , Guanhua Chen

Recent advances in machine learning, particularly in Natural Language Processing (NLP), have produced powerful models trained on vast datasets. However, these models risk leaking sensitive information, raising privacy concerns. In response,…

Machine Learning · Computer Science 2025-09-19 Haoyu Tang , Ye Liu , Xi Zhao , Xukai Liu , Yanghai Zhang , Kai Zhang , Xiaofang Zhou , Enhong Chen

Unlearning in large language models (LLMs) involves precisely removing specific information from a pre-trained model. This is crucial to ensure safety of LLMs by deleting private data or harmful knowledge acquired during pre-training.…

Machine Learning · Computer Science 2025-09-04 Naman Deep Singh , Maximilian Müller , Francesco Croce , Matthias Hein

Large Language Models (LLMs) are smart but forgetful. Recent studies, (e.g., (Bubeck et al., 2023)) on modern LLMs have shown that they are capable of performing amazing tasks typically necessitating human-level intelligence. However,…

Computation and Language · Computer Science 2023-11-08 Eric Melz

Mitigating sensitive and harmful outputs is fundamental to ensuring safe deployment of LLMs. Existing approaches typically follow two paradigms: Knowledge Deletion (KD), which erases undesirable information during training, and…

Machine Learning · Computer Science 2026-05-19 Puning Yang , Junchi Yu , Qizhou Wang , Philip Torr , Bo Han , Xiuying Chen

Unlearning in large language models (LLMs) is critical for regulatory compliance and for building ethical generative AI systems that avoid producing private, toxic, illegal, or copyrighted content. Despite rapid progress, in this work, we…

Machine Learning · Computer Science 2026-05-29 Hadi Reisizadeh , Jiajun Ruan , Yiwei Chen , Soumyadeep Pal , Sijia Liu , Mingyi Hong

The past a few years have witnessed the great success of large language models, demonstrating powerful capabilities in comprehending textual data and generating human-like languages. Large language models achieve success by being trained on…

Computation and Language · Computer Science 2025-03-20 Estrid He , Tabinda Sarwar , Ibrahim Khalil , Xun Yi , Ke Wang