Machine Unlearning

Follow this topic Ask about this topic

Machine unlearning asks how to remove a person’s data, a class, or a learned concept from a model after training, often to support privacy, safety, or changing data rights. Approaches range from exact or certified deletion methods, such as data partitioning and noisy or influence-based updates, to approximate parameter edits, representation changes, and inference-time steering; some systems are designed from the outset to make deletion easier. Researchers evaluate methods against retrained models and test forgetting, retained utility, privacy attacks, recovery, and repeated deletion across language, vision, diffusion, graph, and multimodal systems. A central tension is that suppressed outputs do not necessarily mean information is erased, while stronger removal can damage related knowledge; scalable methods with reliable guarantees and low collateral harm remain a challenge.

Latest papers

354 papers58 papers in the last four weeks, up 76% on the four weeks before. 0.3% of all new papers.

Learning What to Forget: Improving LLM Unlearning via Learned Token-Level Importance
Jun 4, 2026Gizem Yüce, Giorgos Nikolaou, Nicolas FlammarionMachine Unlearning LLM Unlearning
Theory of Machine Learning Lab, EPFL
Short paper: Models in the dark -- Rectification and erasure under GDPR in ML supply chains
Jun 4, 2026Henrik Graßhoff, Malte Hansen, Meiko Jensen +1Machine Unlearning
Karlstad University, Karlstad, Sweden
Exact Unlearning in Reinforcement Learning
Jun 2, 2026Thanh Nguyen-Tang, Raman AroraReinforcement Learning Machine Unlearning
Department of Data Science, New Jersey Institute of Technology, Newark, NJ, USA · Department of Computer Science, Johns Hopkins University, Baltimore, MD, USA
PURGE: Projected Unlearning via Retain-Guided Erasure
Jun 2, 2026Vedant Jawandhia, Daksh Ahuja, Ghufran Alam Siddiqui +3Privacy-Preserving ML Gradient Projection
1BITS Pilani, Pilani Campus, India
Don't Forget Your Embeddings: Robust Knowledge Erasure via Precise Editing of Embeddings
Jun 2, 2026Clara Haya Suslik, Or Shafran, Mor GevaMachine Unlearning LLM Unlearning
Blavatnik School of Computer Science and AI, Tel Aviv University
Multilingual Unlearning in LLMs: Transfer, Dynamics, and Reversibility
Jun 2, 2026Chaoyi Xiang, Olga Ohrimenko, Benjamin I. P. Rubinstein +1Machine Unlearning LLM Unlearning
School of Computing and Information Systems, The University of Melbourne, Melbourne, Australia.
Fast Unlearning at Scale via Margin Self-Correction
Jun 1, 2026Federico Di Gennaro, Alexander Shevchenko, Fanny YangMachine Unlearning LLM Unlearning
ETH Zürich
How Hard Can It Be? Hardness-Aware Multi-Objective Unlearning
Jun 1, 2026Jiangwei Chen, Xinyuan Niu, Rachael Hwee Ling Sim +3Machine Unlearning LLM Unlearning
Department of Computer Science, National University of Singapore, Singapore · Institute for Infocomm Research, Agency for Science, Technology and Research, Singapore · Centre for Frontier AI Research, Agency for Science, Technology and Research, Singapore
SPACE: Source-free Proxy Anchor Concept Erasure for MLLMs
Jun 1, 2026Zhijing Zhang, Jiaqi Ding, Qianshan Wei +5VLM Unlearning Multimodal Large Language Models
School of Computer Science and Engineering, Southeast University · Institute of Automation, Chinese Academy of Sciences
Near-Optimal Machine Unlearning Utility for Smooth Strongly Convex Losses
Jun 1, 2026Matthew Regehr, Gautam Kamath, Andrew LowyStatistical Learning Theory Machine Unlearning
University of Waterloo · University of Waterloo and Vector Institute · CISPA Helmholtz Center for Information Security
Multi-Objective Reference-Aligned Machine Unlearning
May 29, 2026Rasa Khosrowshahli, Stephen Asobiela, Beatrice Ombuki-Berman +1Machine Unlearning Catastrophic Forgetting
Department of Computer Science, Brock University, St. Catharines, ON, Canada · Yousef Haj-Ahmad Department of Engineering, Brock University, St. Catharines, ON, Canada
SUPREME: A Multi-GPU Framework for Reproducible Image Unlearning Method Evaluation
May 29, 2026Petros Andreou, Jamie Lanyon, Axel Finke +1Machine Unlearning Machine Unlearning Evaluation
Department of Computer Science, School of Science, Loughborough University, Loughborough, UK · School of Mathematics, Statistics and Physics, Newcastle University, Newcastle upon Tyne, NE1 7RU, UK
Forgetting Has Neighbors: Localized Collateral Forgetting in Machine Unlearning
May 29, 2026Polina Dolgova, Sebastian U. StichSelf-Supervised Knowledge Distillation Machine Unlearning
CISPA Helmholtz Center for Information Security · Universität des Saarlandes · Saarbrücken, Germany
Divergence Decoding: Inference-Time Unlearning via Auxiliary Models
May 29, 2026Humzah Merchant, Bradford LevyPrivacy Leakage in Language Models Memorization in Generative Models
University of Chicago, Chicago, IL 60637.
De-attribute to Forget for LLM Unlearning
May 29, 2026Xinyang Lu, Jiabao Pan, Rachael Hwee Ling Sim +3Machine Unlearning LLM Unlearning
Department of Computer Science, National University of Singapore, Singapore 117417.
Unlearning in Diffusion Models: A Unified Framework with KL Divergence and Likelihood Constraints
May 29, 2026Shervin Khalafi, Alejandro Ribeiro, Dongsheng DingPrimal-Dual Optimization Diffusion Model Unlearning
University of Pennsylvania · University of Tennessee, Knoxville
AMNESIA: A Large Scale Medical Unlearning Benchmark Suite with Disease-Informed Analysis
May 28, 2026Saeedeh Davoudi, Reihaneh Iranmanesh, Ophir Frieder +1Healthcare Privacy Leakage in Language Models
1IR Lab, Computer Science Department, Georgetown University, Washington D.C.
MAAT: Multi-phase Adapter-Aware Targeted Unlearning
May 28, 2026Suryash Yagnik, Shubham Gaur, Saksham Thakur +3Machine Unlearning LLM Unlearning
1Indian Institute of Information Technology, Bhopal, India · University of California, Santa Cruz, USA · 3Independent Researcher +2
RULER: Representation-Level Verification of Machine Unlearning
May 26, 2026Georgina Cosma, Axel FinkeMachine Unlearning Machine Unlearning Evaluation
Department of Computer Science, Loughborough University, UK · School of Mathematics, Statistics and Physics, Newcastle University, UK
ICCU: In-Context Continual Unlearning via Pattern-Induced Refusal Rules
May 26, 2026Ruihao Pan, Suhang WangRefusal Behavior in Language Models Machine Unlearning
Pennsylvania State University
On the Robustness of Machine Unlearning for Vision-Language Models
May 26, 2026Yujie Lin, Kaidi Jia, Jiayao Ma +2VLM Evaluation VLM Unlearning
1Xiamen University
Visual-Noise Guided In-Context Distillation for Multimodal Large Language Model Unlearning
May 26, 2026Junkai Chen, Yuhao He, Junxiang You +3VLM Unlearning Multimodal Large Language Models
Institute of Automation, Chinese Academy of Sciences · School of Advanced Interdisciplinary Sciences, UCAS
Image Feature Fusion-based Federated Client Unlearning (FCU)
May 26, 2026Hangyi Shen, Yizhi Pan, Tiansuo Li +2Federated Unlearning Mixup
11Hangzhou Medical College, Hangzhou, China
Model Unlearning Objectives Vary for Distinct Language Functions
May 26, 2026Berk Atil, Vipul Gupta, Rebecca J. PassonneauLLM Safety Machine Unlearning
Pennsylvania State University · Scale AI
Continual Speaker Identity Unlearning with Minimal Interference
May 25, 2026Jinju Kim, Yunsung Kang, Gyeong-Moon Park +1TTS Synthesis Zero-Shot TTS
Sungkyunkwan University · Korea University
Concept Unlearning via Cross-Attention Activation Projection for Diffusion Models
May 25, 2026Saemi Moon, Suhyeon Jun, Seoyeon Lee +1Attention Control in Diffusion Models Diffusion Model Unlearning
CSE, POSTECH · GSAI, POSTECH
Closed-Form Node Classification with Exact Graph Unlearning
May 25, 2026Aditya Gaur, Charu SharmaGraph Representation Learning Privacy-Preserving ML
Machine Learning Lab · IIIT Hyderabad
Rethinking Federated Unlearning via the Lens of Memorization
May 23, 2026Jiaheng Wei, Yanjun Zhang, He Zhang +5Federated Unlearning Neural Network Memorization
Royal Melbourne Institute of Technology · Griffith University · Swinburne University of Technology
PIU: Proximity-guided Identity Unlearning in ID-Conditioned Diffusion Models
May 21, 2026Jose Edgar Hernandez Cancino Estrada, Mauro Díaz Lupone, Žiga Emeršič +3Latent Diffusion Models Image Generation
University of Ljubljana, Faculty of Computer and Information Science, Ljubljana, Slovenia · University of Ljubljana, Faculty of Electrical Engineering, Ljubljana, Slovenia
DualOptim+: Bridging Shared and Decoupled Optimizer States for Better Machine Unlearning in Large Language Models
May 20, 2026Xuyang Zhong, Qizhang Li, Yiwen Guo +1Machine Unlearning Multi-Objective Optimization
Department of Computer Science, City University of Hong Kong · Independent Researcher.

Jun 4, 2026J/K move · Enter open · S save

Learning What to Forget: Improving LLM Unlearning via Learned Token-Level Importance

Gizem Yüce, Giorgos Nikolaou, Nicolas Flammarion

Theory of Machine Learning Lab, EPFL

Machine Unlearning LLM Unlearning

Open paper AskPDF arXiv

Machine unlearning aims to remove targeted knowledge from a trained model while preserving its general capabilities. For autoregressive language models, not all tokens in a forget sample are equally relevant to forgetting. Existing approaches either ignore this heterogeneity or rely on auxiliary models, heuristics, or external annotations to estimate each token's relevance for forgetting. We instead characterize it through the interaction with the retain objective: a token is forget-specific to the extent that minimizing the forget loss on that token does not conflict with retain optimality. We formalize this perspective as a joint optimization problem over the model parameters and the token weights and show that, under a natural separation condition, the resulting objective recovers the oracle forget-specific token support. Motivated by this formulation, we introduce Alternating Token-Weighted Unlearning (ATWU), a lightweight framework that jointly learns token forget-specificity and model parameters during unlearning using a simple linear scorer over the hidden states, without external token level supervision. Across TOFU and RWKU, ATWU achieves state of the art forget-retain trade-offs, outperforming sample-level methods, probability-based token weighting heuristics, and auxiliary-model-based approaches. Moreover, the learned scores align substantially better with ground truth forget-specific spans, indicating that ATWU identifies semantically meaningful token level forgetting signals. Overall, our results suggest that retain conflict provides an effective criterion for identifying what language models should forget, enabling unsupervised learning of token level forget-specificity directly from model representations with minimal computational overhead.