arXiv:2507. 19894v2 Announce Type: replace Abstract: With the rapid advancement of generative models, privacy, copyright, safety, and reliability risks have attracted growing attention.
arXiv:2507. 04219v5 Announce Type: replace-cross Abstract: Current unlearning methods for LLMs optimize on the private information they seek to remove by incorporating it into their fine-tuning data.
arXiv:2510. 04773v2 Announce Type: replace Abstract: As Large Language Models (LLMs) demonstrate remarkable capabilities learned from vast corpora, concerns regarding data privacy and safety are receiving increasing attention.
arXiv:2602. 05833v2 Announce Type: replace Abstract: There is a need for synthetic training and test datasets that replicate statistical distributions of original datasets without compromising their confidentiality.
Large Language Models (LLMs) can memorize and reproduce sensitive, copyrighted, or otherwise undesirable training content, creating privacy, safety, and regulatory concerns. Machine unlearning offers...
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.
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:2506. 14003v5 Announce Type: replace Abstract: Machine unlearning (MU) for large language models (LLMs), commonly referred to as LLM unlearning, seeks to remove specific undesirable data or knowledge from a trained model, while maintaining its performance on standard tasks.
arXiv:2607. 28862v1 Announce Type: cross Abstract: The rapid development of Large Language Models (LLMs) has led to significant advances across a wide range of language tasks, while simultaneously raising growing concerns about unauthorized data exploitation and privacy leakage.
arXiv:2606. 16110v1 Announce Type: new Abstract: Machine unlearning has been extensively studied in response to growing privacy concerns and regulatory requirements.
Tokenized Key-Gated Adapter Routing (Locket) is a framework that embeds fine‑grained, policy‑driven access control into large language models by training lightweight LoRA adapters for different privacy policies. A gating module associates a learned keyed entry token with a specific adapter, allowing authorized tokens to unlock private knowledge while invalid or missing tokens trigger privacy‑preserving adapters that redact or sanitize sensitive content. Experiments on datasets such as Enron, ECHR, and Yelp with models like Qwen3, Llama‑3.2, and Gemma‑2‑2B show that Locket maintains perplexity comparable to fine‑tuning when the correct token is provided, and significantly reduces PII leakage when the token is absent or invalid, without sacrificing utility.
arXiv:2606. 09865v1 Announce Type: new Abstract: Privacy and data sharing are often in tension.
arXiv:2605. 00994v2 Announce Type: replace-cross Abstract: Finetuning can significantly modify the behavior of large language models, including introducing harmful or unsafe behaviors.