# Machine unlearning Area: [LLM safety and security](https://mlsanity.com/safety/index.md). HTML: https://mlsanity.com/safety/machine-unlearning/ ## Key facts - Machine unlearning: 1,043 papers on arXiv since 2021 (data through 14 Oct 2026). - 394 of its 1,043 mapped papers (38%) cite “TOFU: A Task of Fictitious Unlearning for LLMs” (2024, arXiv 2401.06121). - 354 of its 1,043 mapped papers (34%) cite “Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning” (2024, arXiv 2404.05868). - 52 new papers 24 Sep–14 Oct. ## Most cited here - [TOFU: A Task of Fictitious Unlearning for LLMs](https://mlsanity.com/paper/2401.06121/) (2024), cited by 394 papers here - [Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning](https://mlsanity.com/paper/2404.05868/) (2024), cited by 354 papers here - [Knowledge Unlearning for Mitigating Privacy Risks in Language Models](https://mlsanity.com/paper/2210.01504/) (2022), cited by 299 papers here - [Who's Harry Potter? Approximate Unlearning in LLMs](https://mlsanity.com/paper/2310.02238/) (2023), cited by 267 papers here - [Remember What You Want to Forget: Algorithms for Machine Unlearning](https://mlsanity.com/paper/2103.03279/) (2021), cited by 252 papers here - [Unrolling SGD: Understanding Factors Influencing Machine Unlearning](https://mlsanity.com/paper/2109.13398/) (2021), cited by 232 papers here - [SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation](https://mlsanity.com/paper/2310.12508/) (2023), cited by 212 papers here - [MUSE: Machine Unlearning Six-Way Evaluation for Language Models](https://mlsanity.com/paper/2407.06460/) (2024), cited by 212 papers here - [Towards Unbounded Machine Unlearning](https://mlsanity.com/paper/2302.09880/) (2023), cited by 209 papers here - [Large Language Model Unlearning](https://mlsanity.com/paper/2310.10683/) (2023), cited by 206 papers here ## New (24 Sep–14 Oct) - [Are We Really Measuring Forgetting? Pitfalls in Evaluating Machine Unlearning for Multimodal LLMs](https://mlsanity.com/paper/2610.19613/) (2026-10-14) - [RA2: Retain-Anchored Attraction Preserves Forget-Adjacent Utility in LLM Unlearning](https://mlsanity.com/paper/2610.19385/) (2026-10-14) - [Can Agents Forget When Asked? A Benchmark for Memory Unlearning in LLM Agents](https://mlsanity.com/paper/2610.18052/) (2026-10-13) - [Counterfactual Certification for Sequential Unlearning with Long-Run Performance Guarantees](https://mlsanity.com/paper/2610.17993/) (2026-10-13) - [Can Agents Truly Forget? Explore Machine Unlearning for LLM Agents](https://mlsanity.com/paper/2610.17659/) (2026-10-13) - [Decouple to Forget: Semantic Mediation for Sensitive Unlearning in Large Language Models](https://mlsanity.com/paper/2610.17654/) (2026-10-13) - [CUSE: Fine-Grained Multimodal Unlearning with Counterfactual Guidance and On-Policy Self-Distillation](https://mlsanity.com/paper/2610.14763/) (2026-10-10) - [Decoupling Knowledge Forgetting and Refusal Learning in MLLM Unlearning](https://mlsanity.com/paper/2610.14605/) (2026-10-10) - [Compositional Concepts Erasing: Disentangling Object-Style via Domain Manifold Unlearning](https://mlsanity.com/paper/2610.14514/) (2026-10-10) - [REDaCT: Collapse-Free Unlearning in Large Reasoning Models](https://mlsanity.com/paper/2610.12769/) (2026-10-08) - [Not Every Change Is Necessary: Recoverable Drift in Large Language Model Unlearning](https://mlsanity.com/paper/2610.11915/) (2026-10-08) - [Minimax Gaussian Mechanisms for Continual Machine Unlearning](https://mlsanity.com/paper/2610.11628/) (2026-10-08) - [Enabling Preference-driven Unlearning in Few-step Distilled Text-to-Image Diffusion Models](https://mlsanity.com/paper/2610.10859/) (2026-10-07) - [Nullify: Null-Space Activation Steering for Training-Free LLM Unlearning](https://mlsanity.com/paper/2610.10655/) (2026-10-07) - [Why Forget-Only Unlearning Needs Memorization](https://mlsanity.com/paper/2610.10519/) (2026-10-07) - [Open-MMUnlearning: Unifying Methods and Evaluation for MLLM Unlearning](https://mlsanity.com/paper/2610.10358/) (2026-10-07) - [How Learning Governs Unlearning across the Memorization-Generalization Spectrum](https://mlsanity.com/paper/2610.08577/) (2026-10-06) - [Exact Unlearning via Quantized Sufficient Statistics](https://mlsanity.com/paper/2610.07197/) (2026-10-05) - [Your Unlearning Gives You Away: Identifying Erased Concepts in Diffusion Models](https://mlsanity.com/paper/2610.05601/) (2026-10-04) - [No Concept Escapes the Audit: Auditing-Aware Unlearning for Verifiable Concept Erasure in Diffusion Models](https://mlsanity.com/paper/2610.05401/) (2026-10-04) - [UnAct: Gradient-Free Unlearning via Targeted Activation Intervention](https://mlsanity.com/paper/2610.04426/) (2026-10-03) - [Modeling Deletion Requests in Machine Unlearning](https://mlsanity.com/paper/2610.04310/) (2026-10-03) - [Certified Mechanistic Edits: Behavioral Guarantees for Skill Removal and Preservation](https://mlsanity.com/paper/2610.03502/) (2026-10-02) - [On Unlearning for Time-series Forecasting](https://mlsanity.com/paper/2610.02865/) (2026-10-02) - [From Mathematical to Executable Certificates for Machine Unlearning](https://mlsanity.com/paper/2610.02268/) (2026-10-01) - [SIEVE: Selective attention-value Suppression for Vision-Language Models Unlearning](https://mlsanity.com/paper/2610.01962/) (2026-10-01) - [Repurposing Obsolete Representations for Post-Deployment Adaptation](https://mlsanity.com/paper/2610.01453/) (2026-10-01) - [Linguistic Loopholes in LLM Unlearning: From a 174-Language Benchmark to Coverage-Aware Unlearning](https://mlsanity.com/paper/2609.40286/) (2026-09-30) - [LLM Persona Unlearning](https://mlsanity.com/paper/2609.39882/) (2026-09-30) - [Learning What to Forget: Distributional Unlearning for LLM Representation Spaces](https://mlsanity.com/paper/2609.38929/) (2026-09-30)