Metraipolis › archive › dc_2571fa4a9593
GROM: Gradient-Free Rapid One-Shot Machine Unlearning — arXiv:2608.05783
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.05783
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-25T21:31:08.426Z
- SHA-256 of the archived text
3bed697c0dfc38315ba3e7c493c43abc0eedb01a95bddcd6524af1ffc77d0187- Stable URL of this page
https://metraipolis.com/documento/dc_2571fa4a9593
How to cite
GROM: Gradient-Free Rapid One-Shot Machine Unlearning — arXiv:2608.05783 — arXiv (en), https://arxiv.org/abs/2608.05783 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2571fa4a9593 (Metraipolis archive dc_2571fa4a9593, sha256 3bed697c0dfc38315ba3e7c493c43abc0eedb01a95bddcd6524af1ffc77d0187)
BibTeX
@misc{dc2571fa4a9593,
title = {GROM: Gradient-Free Rapid One-Shot Machine Unlearning — arXiv:2608.05783},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.05783},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2571fa4a9593; sha256 3bed697c0dfc38315ba3e7c493c43abc0eedb01a95bddcd6524af1ffc77d0187},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.05783. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Machine unlearning has become a critical capability for safely removing specific, sensitive knowledge from large language models (LLMs). Current state-of-the-art approaches primarily rely on iterative, training-time unlearning via fine-tuning. However, even when utilizing parameter-efficient dimensionality reduction techniques like LoRA, gradient-based optimization remains computationally expensive and lacks explicit analytical formulations. It can also leave the targeted knowledge merely hidden rather than removed, to the point that simply quantizing the unlearned model restores much of what it was supposed to have erased. To resolve this, we propose a novel one-shot unlearning approach, abandoning iterative optimization in favor of a direct, exact analytical solution. We frame the unlearning process as a ridge-regularized least-squares optimization problem, deriving a closed-form additive update for targeted weight matrices. This update forces the selected layer to suppress unwanted content while strictly preserving its behavior on retained data. Computed from gradient-free forward passes alone, with no backpropagation and no iteration to convergence, GROM applies the weight edit in mere seconds, which makes it orders of magnitude faster than traditional fine-tuning. Extensive evaluations demonstrate that GROM achieves state-of-the-art forgetting-utility trade-offs on TOFU-5%, TOFU-10%, MUSE-Books, MUSE-News and WMDP, significantly reducing computational overhead without sacrificing overall model performance. Because the update removes the targeted content from the weights instead of masking it, GROM also withstands the low-bit quantization attack that recovers much of the content a gradient-based baseline had appeared to forget. Our code is publicly available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-07 in cs.CL). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2608.05783 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-25T21:24:38.262Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).