Machine Unlearning

Ask about this topic

Overview

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

CardsList

351 papers56 papers in the last four weeks, up 70% on the four weeks before. 0.3% of all new papers.

  1. The Nearest Target Is the Wrong One: Target Separation in Arc2Face Identity Unlearning

    Aug 30, 2026Zeynel TokMachine Unlearning

    University of Oxford, UK

  2. Forget or Fine-tune? A Comparative Study of Machine Unlearning Strategies for Noisy Label Correction

    Aug 30, 2026João L. P. Santana, Filipe R. CordeiroNoisy-Label LearningClassification

    Department of Computing Universidade Federal Rural de Pernambuco, Brazil

  3. On the Recoverability of Private Information Unlearning in Large Language Models

    Aug 30, 2026Shicheng Hu, Runzhi Tian, Ziqiao Wang +1LLM AuditingPrivacy Leakage in Language Models

    University of Illinois Urbana-Champaign · University of Ottawa · Tongji University

  4. On the Plasticity Collapse in Continual Machine Unlearning

    Aug 30, 2026Yingdan Shi, Xiang Xu, Kaize Ding +2Machine UnlearningLoss of Plasticity

    Illinois Institute of Technology, Chicago IL 60616, USA · Amazon, New York NY 10001, USA · Northwestern University, Evanston IL 60208, USA +1

  5. Unlearning on Spatio-Temporal Graphs through Subgraph Virtual Edge Reconstruction

    Aug 29, 2026Qiming Guo, Wenbo Sun, Chen Pan +2Graph UnlearningMachine Unlearning

    Texas A&M University - Corpus Christi Corpus Christi, Texas, USA · Delft University of Technology Delft, Netherlands · University of Texas at San Antonio San Antonio, Texas, USA +1

  6. Spatial Entropy based Partitioning for Spatiotemporal Graph Unlearning

    Aug 29, 2026Qiming Guo, Wenbo Sun, Ye Wang +1Graph PartitioningGraph Unlearning

    Texas A&M University - Corpus Christi, Corpus Christi, TX, USA · Delft University of Technology, Netherlands · Biogen, Cambridge, MA, USA

  7. GRACE:Gradient-guided Coreset Selection for LLM Unlearning

    Aug 28, 2026Praveen Bushipaka, Andrea D'Angelo, Lucia Passaro +1Machine UnlearningLLM Unlearning

    University of Pisa, Pisa, Italy · Scuola Superiore Sant’Anna, Pisa, Italy · Aarhus University, Aarhus, Denmark

  8. AIM: Anchor Identity Features, Then Match for Multimodal Large Language Model Unlearning

    Aug 28, 2026Wonjun Lee, Jaehyuk Jang, Kangwook Ko +2MLLM UnlearningPrivacy Protection in VLMs

    Korea Advanced Institute of Science and Technology (KAIST) Daejeon, Republic of Korea

  9. Graph-Guided Selective Unlearning for Language Models: Controlling Support Routes Beyond Forget Seeds

    Aug 27, 2026Waqas Khan, Tabinda Sarwar, Jingyue Cong +2Machine UnlearningLLM Unlearning

  10. ST2^2U: Stateful Test-Time Unlearning via Restricted Knowledge Boundary Control

    Aug 24, 2026Xunlei Chen, Qinghui Gong, Ruini Xue +3LLM UnlearningMachine Unlearning

    University of Electronic Science and Technology of China · Southwest Jiaotong University

  11. Unlearning Is Not Just Erasing: Temporal Decoupling via Generation Inequality

    Aug 24, 2026Xunlei Chen, Qirui Ye, Yuang Li +5Machine UnlearningLLM Unlearning

    School of Information and Software Engineering, University of Electronic Science and Technology of China · School of Computer Science and Engineering, University of Electronic Science and Technology of China

  12. BLADE: Bilevel Low-rank Augmented-Lagrangian Erasure for LLM Unlearning

    Aug 23, 2026Md Toufikuzzaman, Ahmad Mousavi, Dongwon LeeMachine UnlearningLLM Unlearning

    The Pennsylvania State University, USA · American University

  13. Stress Testing Unlearning Algorithms

    Aug 23, 2026Noam Diamant, Neta Glazer, Ethan FetayaLLM Safety BenchmarksMachine Unlearning

    Bar-Ilan University

  14. Can LLMs Truly Forget? Revealing Unlearning Gaps Through Adversarial Evaluation

    Aug 21, 2026Ayush Gupta, Hima Varshini Surisetty, Sreevidya Bollineni +5Machine UnlearningLLM Unlearning

    University of Massachusetts Amherst · Microsoft Corporation

  15. Can Scientific Claims Be Removed from Large Language Models? A Systematic Evaluation of Claim-Level Unlearning

    Aug 21, 2026Snigdha Paul, Manasi Patwardhan, Arman CohanLLM UnlearningMachine Unlearning

    TCS Research, India · Yale University, USA

  16. Cross-Domain Generalization in Machine Unlearning via Label-Conditioned Energy Magnitude Regularization

    Aug 18, 2026Syed Ali Ahmed, Syed Bilal Ahsan, Muhammad Zaigham ZaheerMachine UnlearningCross-Domain Generalization

    National University of Computer and Emerging Sciences, Karachi, Pakistan · Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE

  17. Learning to Unlearn: Machine Unlearning via Learning the Unlearning Behaviors

    Aug 17, 2026Hang Zhang, Kaifeng Zhang, Yixiao Ma +3Machine UnlearningPrivacy-Preserving ML

    State Key Laboratory for Novel Software Technology Nanjing University Nanjing, China · Centre for Cyber Resilience and Trust Deakin University Burwood, VIC, Australia

  18. SAUL: Sharpness-Aware Augmented-Lagrangian Unlearning

    Aug 17, 2026Jaewan Choi, Junyoung Yang, Sangdon ParkMachine UnlearningLLM Unlearning

    Computer Science and Engineering, POSTECH · Graduate School of Artificial Intelligence, POSTECH

  19. Spectral Saliency for Machine Unlearning

    Aug 16, 2026Cedar Site Bai, Amber Yijia Zheng, Raymond A. Yeh +1Machine UnlearningLLM Unlearning

    Department of Computer Science Purdue University

  20. What to Forget in Unlearning? Forget Set Curation for Language Models

    Aug 14, 2026Animesh Jha, Arpandeep Khatua, Youssef Allouah +1Machine UnlearningLLM Unlearning

    Stanford University

  21. The More Popular, The Harder to Forget: Adaptive Popularity for LLM Unlearning

    Aug 14, 2026Anna Borisiuk, Andrey Savchenko, Alexander Panchenko +1Machine UnlearningLLM Unlearning

    AIRI · ISP RAS Research Center for Trusted Artificial Intelligence · Sber AI Lab +1

  22. MapRoute++: Surrogate-Guided Semantic Routing for Visual Concept Unlearning

    Aug 13, 2026Ashok Urlana, L. D. M. S. Sai Teja, Vivek Hruday Kavuri +1Diffusion Model UnlearningMachine Unlearning

    1IIIT Hyderabad · 2TCS Research, India · 3NIT Silchar

  23. Machine Unlearning for Speech Question Answering in Large Audio-Language Models

    Aug 13, 2026Zhe LiuMachine UnlearningMLLM Unlearning

    Meta Platforms, Inc. Menlo Park, USA

  24. Can You Delete a Year of Market Data? Machine Unlearning Against Exact Retraining Oracles

    Aug 13, 2026Junyi YeMachine UnlearningMachine Unlearning Evaluation

    School of Computing, Montclair State University Montclair, New Jersey, USA

  25. LEMUR: Latent Entropy-aware Multimodal Unlearning via Visual-anchored Reasoning Redirection

    Aug 12, 2026Xinhao Zhong, Yuxia Qiao, Junhao Li +3VLM UnlearningMultimodal Large Language Models

    3Pengcheng Laboratory · 1Harbin Institute of Technology, Shenzhen · 2Tsinghua University

  26. Measure, Don't Optimize: Forecasting Recovery in LLM Unlearning

    Aug 11, 2026Zirui Song, Huaxing Liu, Xiang Wang +8LLM AuditingMachine Unlearning

    Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) · AMAP, Alibaba Group · Peking University

  27. PRMU: A Corpus-Free Benchmark for Person-Centric Knowledge Unlearning in Multimodal Large Language Models

    Aug 11, 2026Huafeng Chen, Yueming Lyu, Ziyuan Chen +4MLLM UnlearningMachine Unlearning

    School of Intelligence Science and Technology, Nanjing University · Department of Computing, Imperial College London

  28. GROM: Gradient-Free Rapid One-Shot Machine Unlearning

    Aug 6, 2026Paweł Batorski, Przemysław Spurek, Paul SwobodaMachine UnlearningLLM Unlearning

    1Heinrich Heine University Düsseldorf · 2Jagiellonian University · 3IDEAS Research Institute

  29. Trajectory-Guided Forget-Recover Network for Continual LLM Unlearning

    Aug 4, 2026Zezheng Wu, Xinghe Cheng, Qinggang Zhang +4Machine UnlearningLLM Unlearning

    Guilin University of Electronic Technology · Jinan University · Jilin University +2

  30. SCOPE: Entanglement Frontier Escape for Source-Free Class Unlearning

    Aug 3, 2026Junhao Cai, Dohun Kim, Sung Il Choi +4Machine Unlearning

    Korea University, Seoul, Republic of Korea