English
Related papers

Related papers: Parameter-Efficient Token Embedding Editing for Cl…

200 papers

Large Language Models (LLMs) inevitably acquire harmful information during training on massive datasets. LLM unlearning aims to eliminate the influence of such harmful information while maintaining the model's overall performance. Existing…

Computation and Language · Computer Science 2025-03-07 Wenyu Wang , Mengqi Zhang , Xiaotian Ye , Zhaochun Ren , Zhumin Chen , Pengjie Ren

Although large vision-language models (LVLMs) leverage rich visual token representations to achieve strong performance on multimodal tasks, these tokens also introduce significant computational overhead during inference. Existing…

Machine Learning · Computer Science 2025-05-20 Yichen Guo , Hanze Li , Zonghao Zhang , Jinhao You , Kai Tang , Xiande Huang

Training machine learning models requires the storage of large datasets, which often contain sensitive or private data. Storing data is associated with a number of potential risks which increase over time, such as database breaches and…

Machine Learning · Computer Science 2026-04-14 Aviraj Newatia , Michael Cooper , Viet Nguyen , Rahul G. Krishnan

Machine Unlearning (MU) aims to remove target training data from a trained model so that the removed data no longer influences the model's behavior, fulfilling "right to be forgotten" obligations under data privacy laws. Yet, we observe…

Cryptography and Security · Computer Science 2026-01-27 Jaeung Lee , Suhyeon Yu , Yurim Jang , Simon S. Woo , Jaemin Jo

Machine learning systems increasingly face requirements to remove entire domains of information--such as toxic language or biases--rather than individual user data. This task presents a dilemma: full removal of the unwanted domain data is…

Machine Learning · Computer Science 2026-01-15 Youssef Allouah , Rachid Guerraoui , Sanmi Koyejo

Parameter-efficient fine-tuning (PEFT) of pre-trained language models (PLMs) has emerged as a highly successful approach, with training only a small number of parameters without sacrificing performance and becoming the de-facto learning…

Computation and Language · Computer Science 2023-10-20 Baohao Liao , Shaomu Tan , Christof Monz

Token pruning is essential for enhancing the computational efficiency of vision-language models (VLMs), particularly for video-based tasks where temporal redundancy is prevalent. Prior approaches typically prune tokens either (1) within the…

Computer Vision and Pattern Recognition · Computer Science 2026-03-19 Jianrui Zhang , Yue Yang , Rohun Tripathi , Winson Han , Ranjay Krishna , Christopher Clark , Yong Jae Lee , Sangho Lee

The Unlearning Sensitive Content from Large Language Models task aims to remove targeted datapoints from trained models while minimally affecting their general knowledge. In our work, we leverage parameter-efficient, gradient-based…

Machine unlearning aims to remove the contribution of designated training data from a trained model while preserving performance on the remaining data. Existing work mainly focuses on single-task settings, whereas modern models often…

Artificial Intelligence · Computer Science 2026-05-20 Ying-Hua Huang , Rui Fang , Hsi-Wen Chen , Ming-Syan Chen

The practical needs of the ``right to be forgotten'' and poisoned data removal call for efficient \textit{machine unlearning} techniques, which enable machine learning models to unlearn, or to forget a fraction of training data and its…

Computer Vision and Pattern Recognition · Computer Science 2023-03-22 Min Chen , Weizhuo Gao , Gaoyang Liu , Kai Peng , Chen Wang

Fine-tuning BERT-based models is resource-intensive in memory, computation, and time. While many prior works aim to improve inference efficiency via compression techniques, e.g., pruning, these works do not explicitly address the…

Computation and Language · Computer Science 2022-08-04 Danilo Vucetic , Mohammadreza Tayaranian , Maryam Ziaeefard , James J. Clark , Brett H. Meyer , Warren J. Gross

Recent work in machine learning for healthcare has raised concerns about patient privacy and algorithmic fairness. For example, previous work has shown that patient self-reported race can be predicted from medical data that does not…

Machine Learning · Computer Science 2023-11-14 Wei Liao , Joel Voldman

Recent advances in large reasoning models (LRMs) have enabled strong chain-of-thought (CoT) generation through test-time computation. While these multi-step reasoning capabilities represent a major milestone in language model performance,…

Artificial Intelligence · Computer Science 2025-10-14 Changsheng Wang , Chongyu Fan , Yihua Zhang , Jinghan Jia , Dennis Wei , Parikshit Ram , Nathalie Baracaldo , Sijia Liu

Machine unlearning enables data holders to remove the contribution of their specified samples from trained models to protect their privacy. However, it is paradoxical that most unlearning methods require the unlearning requesters to firstly…

Cryptography and Security · Computer Science 2026-01-13 Weiqi Wang , Zhiyi Tian , Chenhan Zhang , Shui Yu

The machine learning community is increasingly recognizing the importance of fostering trust and safety in modern generative AI (GenAI) models. We posit machine unlearning (MU) as a crucial foundation for developing safe, secure, and…

Computer Vision and Pattern Recognition · Computer Science 2025-03-04 Tianqi Chen , Shujian Zhang , Mingyuan Zhou

Although language models (LMs) demonstrate exceptional capabilities on various tasks, they are potentially vulnerable to extraction attacks, which represent a significant privacy risk. To mitigate the privacy concerns of LMs, machine…

Computation and Language · Computer Science 2024-06-21 Dohyun Lee , Daniel Rim , Minseok Choi , Jaegul Choo

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

Machine unlearning (MU) addresses privacy risks in pretrained models. The main goal of MU is to remove the influence of designated data while preserving the utility of retained knowledge. Achieving this goal requires preserving semantic…

Computer Vision and Pattern Recognition · Computer Science 2026-03-16 Kiseong Hong , JungKyoo Shin , Eunwoo Kim

Transformer has become fundamental to a vast series of pre-trained large models that have achieved remarkable success across diverse applications. Machine unlearning, which focuses on efficiently removing specific data influences to comply…

Machine Learning · Computer Science 2025-08-26 Wenjie Bao , Jian Lou , Yuke Hu , Xiaochen Li , Zhihao Liu , Jiaqi Liu , Zhan Qin , Kui Ren

Pre-training of Large Language Models is often prohibitively expensive and inefficient at scale, requiring complex and invasive modifications in order to achieve high data throughput. In this work, we present Token-Superposition Training…

Computation and Language · Computer Science 2026-05-20 Bowen Peng , Théo Gigant , Jeffrey Quesnelle