The paper introduces Quantized Sufficient Statistics (QSS), a method that separates a frozen global schema from mutable, sum‑decomposable content to enable exact unlearning. QSS offers two variants: QSS‑L, which removes a label while keeping the input, and QSS‑E, which removes both input and label by learning a schema without deletable examples. Experiments on 15 vision, text, and tabular datasets show that QSS‑L achieves deletion latencies up to 483× faster than SISA while maintaining comparable accuracy, and QSS‑E quantifies the accuracy trade‑off when all traces of an input are removed.
By Ami Tavory, Shripad Gade, Tal Sarig, Noam Touitou, Ido Guy
arXiv:2605. 07482v2 Announce Type: replace Abstract: Machine unlearning for large language models (LLMs) aims to selectively remove memorized content such as private data, copyrighted text, or hazardous knowledge, without costly full retraining.
By Zizhao Hu, Ameya Godbole, Johnny Tian-Zheng Wei, Mohammad Rostami, Jesse Thomason, Robin Jia
arXiv:2506.10946v3 Announce Type: replace-cross
Abstract: Unlearning large language models (LLMs) is important due to copyright and privacy concerns. A key challenge is unintended forgetting, where r...
By Peizhi Niu, Evelyn Ma, Boya Hou, Huiting Zhou, Duo Zhou, Huan Zhang, S. Rasoul Etesami, Olgica Milenkovic
The paper introduces MoME, a switchable unlearning framework for re-identification models that allows a single backbone to operate in either Full mode (standard inference) or Core mode (unlearned inference). MoME partitions the backbone into core parameters that retain retrieval capability and zero‑initialized parasitic parameters that store full‑data knowledge, training them with gradient isolation so the core never receives forget‑set gradients. The authors demonstrate that Core mode satisfies deletion requests with a simple flag flip, prove its independence from the forget set, and validate its effectiveness on Market‑1501, VeRi‑776, and RegDB using ResNet and CLIP backbones.
By Jingong Chen, Kyle Gao, Guangyuan Li, Chulwoo Pack, Sijia Liu, Kwanghee Won
arXiv:2605. 20341v2 Announce Type: replace-cross Abstract: Federated learning systems must support data deletion requests to comply with privacy regulations, yet retraining from scratch after each deletion is computationally prohibitive.
By Ali Mahdavi, Azadeh Zamanifar, Amirfarhad Farhadi, Omid Kashefi
The paper introduces Forgetting Only What Matters via Unlearning Layers (FOM-UL), a layer‑selective unlearning framework for large language models. FOM-UL uses a forget‑to‑retain significance score to identify transformer layers that strongly influence the forget set while being insensitive to the retain set, allowing targeted updates that preserve most of the model. Experiments on TOFU, KnowUnDo, and MUSE-style benchmarks show that FOM-UL reduces residual memorization and maintains utility better than several baselines, even after 8‑bit and 4‑bit post‑training quantization, and it also limits recovery of forgotten content in adversarial prompt tests.
By Ravi Ranjan, Olivera Kotevska, Agoritsa Polyzou