Output Vector Editing (OVE) is a post‑hoc technique that suppresses unwanted text continuations from large language models by editing the output vectors of specific neurons. It uses a two‑stage localization of MLP layers and neurons combined with full‑vocabulary least‑squares updates, and its multi‑anchor variant (OVE‑MA) adaptively selects continuation positions to maximize suppression. Experiments on models ranging from 360 M to 7 B parameters show that OVE‑MA can reduce recoverable continuations by 24.45 % with only five output‑vector updates, outperforming the prior method REVS while requiring far fewer updates.
arXiv:2511. 05852v4 Announce Type: replace-cross Abstract: Knowledge editing (KE) offers a lightweight alternative to retraining for updating large language models (LLMs).
arXiv:2610.09835v1 Announce Type: new Abstract: Continual pre-training and fine-tuning in Large Language Models (LLMs) inevitably induce catastrophic forgetting, typically mitigated by replay using o...
The paper introduces a token‑level log‑likelihood ratio to pinpoint where large language models memorize training sequences. It proposes a probe‑steer framework, instantiated as Gated Subspace Steering (GSS), that selectively corrects memorization‑relevant activations using the leading singular vectors of a gradient‑weighted activation matrix. Experiments on four benchmarks show GSS matches or surpasses state‑of‑the‑art memorization reduction methods while using 10–100× less compute.
The paper explores ways to reduce the memorization of training data in language models, testing three regularizer-based, three finetuning-based, and eleven machine unlearning methods—five of which are newly introduced. It introduces TinyMem, a lightweight suite of small models for rapid testing of these mitigation techniques, and shows that unlearning methods, particularly BalancedSubnet, outperform others in removing memorized content while maintaining task performance. The study also finds that regularizer-based approaches are slow and ineffective, while finetuning methods are costly, especially when high accuracy is required.
The paper investigates how tokenization can undermine post‑release guarantees that sensitive knowledge has been edited or unlearned from open‑weight large language models. By showing that alternative valid tokenizations can bypass localized modifications, the authors introduce Toketive, a reference‑free attack that detects modified knowledge and reconstructs pre‑edit responses using only the released model. Experiments on five LLMs, six datasets, and six editing techniques reveal that 38.6% of alternative tokenizations recover suppressed information, with Toketive achieving high detection and reconstruction accuracy.
arXiv:2606. 13705v1 Announce Type: cross Abstract: Yes.
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.
arXiv:2605. 12765v3 Announce Type: replace Abstract: Large Language Models memorize vast amounts of training data, raising concerns regarding privacy, copyright infringement, and safety.
arXiv:2607. 20433v1 Announce Type: cross Abstract: While language models remain frozen at their training state, the world evolves continuously.
The paper introduces ADU, a fine‑grained training framework that unlearns sensitive information from large language models by decoupling contextual attention pathways instead of erasing tokens. ADU exploits the distinction between local and global attention heads to identify and suppress attention paths that retrieve persistent sensitive anchors, while preserving local‑attention structure and overall language modeling performance. Evaluation on the TOFU and WMDP benchmarks shows ADU achieves superior forget quality (0.93 on TOFU) and retains 92.9% of model utility compared to 81.9% for existing baselines, with fewer side effects in benign contexts.
Large Language Models (LLMs) can memorize and reproduce sensitive, copyrighted, or otherwise undesirable training content, creating privacy, safety, and regulatory concerns. Machine unlearning offers...
arXiv:2607. 22663v1 Announce Type: new Abstract: Block diffusion has emerged as the dominant paradigm for scaling discrete diffusion language models (dLLMs), because decoding text in fixed-size blocks preserves parallel generation within each block while keeping the quadratic attention cost tractable.