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

372 papers34 papers in the last four weeks, down 40% on the four weeks before. 0.2% of all new papers.

  1. Not All Change Is Damage: Update-Matched Unlearning for Large Language Models

    Oct 15, 2026Jie Li, Youming Tao, Bowei He +1Machine UnlearningLLM Unlearning

  2. Are We Really Measuring Forgetting? Pitfalls in Evaluating Machine Unlearning for Multimodal LLMs

    Oct 14, 2026Oscar Chew, Po-Yi Lu, Yi-Jie Cheng +4MLLM UnlearningMachine Unlearning

  3. RA2^2: Retain-Anchored Attraction Preserves Forget-Adjacent Utility in LLM Unlearning

    Oct 14, 2026Zinan Ling, Yang Xiao, Ruimeng Ye +2Machine UnlearningLLM Unlearning

  4. Can Agents Forget When Asked? A Benchmark for Memory Unlearning in LLM Agents

    Oct 13, 2026Bofan Xie, Chaokun Wang, Guanchen Ge +4LLM Agent MemoryMemory Agent Benchmarks

  5. Can Agents Truly Forget? Explore Machine Unlearning for LLM Agents

    Oct 13, 2026Junkai Lin, Ge Xu, Zheng Xu +2Machine UnlearningLLM Unlearning

  6. CUSE: Fine-Grained Multimodal Unlearning with Counterfactual Guidance and On-Policy Self-Distillation

    Oct 10, 2026Chenlu Ding, Jiancan Wu, Yanchen Luo +4MLLM UnlearningMachine Unlearning

  7. Compositional Concepts Erasing: Disentangling Object-Style via Domain Manifold Unlearning

    Oct 10, 2026Yang Xiao, Kaiyuan Deng, Gen Li +4Diffusion Model UnlearningMachine Unlearning

  8. REDaCT: Collapse-Free Unlearning in Large Reasoning Models

    Oct 8, 2026Joshua Maccoby, Wendy Hui WangMachine UnlearningLLM Unlearning

  9. Not Every Change Is Necessary: Recoverable Drift in Large Language Model Unlearning

    Oct 8, 2026Xunlei Chen, Qinghui Gong, Jingkun Xue +3Machine UnlearningLLM Unlearning

  10. Minimax Gaussian Mechanisms for Continual Machine Unlearning

    Oct 8, 2026Qi Kuang, Yin XiaContinual Machine UnlearningMachine Unlearning

  11. Why Forget-Only Unlearning Needs Memorization

    Oct 7, 2026Luka Radić, Vikrant Singhal, Amartya SanyalMachine Unlearning

  12. Removing Information Content Does Not Certify Tamper Resistance in Open-Weight Models

    Oct 6, 2026Domenic Rosati, Alessa Carbo, Ali Dadsetan +5Certified RobustnessMachine Unlearning

  13. How Learning Governs Unlearning across the Memorization-Generalization Spectrum

    Oct 6, 2026Hwiyeong Lee, Hyelim Lim, Ingyu Bang +2Memorization in Language ModelsMachine Unlearning

  14. Exact Unlearning via Quantized Sufficient Statistics

    Oct 5, 2026Ami Tavory, Shripad Gade, Tal Sarig +2Machine UnlearningMachine Unlearning Evaluation

  15. Your Unlearning Gives You Away: Identifying Erased Concepts in Diffusion Models

    Oct 4, 2026Kaiyuan Deng, Yuchen Li, Yang Xiao +3Diffusion Model UnlearningConcept Erasure

  16. UnAct: Gradient-Free Unlearning via Targeted Activation Intervention

    Oct 3, 2026Saeed Abdul Muizz, Aayat Rafiq, Iqra Altaf Gillani +1Machine Unlearning

  17. Modeling Deletion Requests in Machine Unlearning

    Oct 3, 2026Christian Cianfarani, Aloni CohenMachine Unlearning

  18. FADE: Frame-Aware Diffusion-Transformer-based Multi-Concept Erasure for Video Unlearning

    Oct 2, 2026Yuchen Li, Kaiyuan Deng, Chaoran Feng +2Diffusion Model UnlearningMachine Unlearning

  19. Certified Mechanistic Edits: Behavioral Guarantees for Skill Removal and Preservation

    Oct 2, 2026Md Sazid Uddin, Md. Khairul Alam Mazumder, M. F. MridhaMachine UnlearningNeural Network Verification

  20. On Unlearning for Time-series Forecasting

    Oct 2, 2026Zeyu Shi, Yanhui Luo, Ziming Hong +4Machine UnlearningTime Series Forecasting

  21. SIEVE: Selective attention-value Suppression for Vision-Language Models Unlearning

    Oct 1, 2026Si Qi Goh, Cap Dang Xuan Kiet, Tat-Jen Cham +1VLM UnlearningPrivacy-Preserving Language Models

  22. Repurposing Obsolete Representations for Post-Deployment Adaptation

    Oct 1, 2026Daniel Bethell, Charmaine Barker, Simos GerasimouModel EditingMachine Unlearning

  23. When Is Deletion Ordering Tractable? From Update Dynamics to Permutation Structure

    Oct 1, 2026Xinyu Wang, Ziyu Zhao, Yixuan He +1Combinatorial OptimizationMachine Unlearning

  24. From Mathematical to Executable Certificates for Machine Unlearning

    Oct 1, 2026Ziyu Zhao, Xinyu Wang, Xiaowen Chang +1Machine UnlearningMachine Unlearning Evaluation

  25. State-Space Unlearning for Non-Stationary Bias in Land Surface Forecasting

    Sep 30, 2026Anidipta PalMachine UnlearningState Space Models

  26. LLM Persona Unlearning

    Sep 30, 2026Kemou Li, Zhuan Shi, Qizhou Wang +4Model EditingPersona-Conditioned Generation

  27. FOMO: Forget the Concept, Don't Miss Out on the Scene in Selective Video Unlearning

    Sep 30, 2026Łukasz Rudnik, Agnieszka Polowczyk, Alicja Polowczyk +1Video Diffusion ModelsDiffusion Model Unlearning

  28. Faithful Dual-constrained Erasure for Robust LLM Safety Alignment

    Sep 30, 2026Jiaqing Li, Shide Zhou, Zhibo Zhang +3LLM Safety AlignmentMachine Unlearning