Cascade is a hierarchical recoverability control framework designed to improve large language model unlearning. It combines path-level routing, representation-level compression, and decoding-level intervention to minimize the internal identifiability of target knowledge. Experiments on TOFU, MUSE-News, and WMDP demonstrate that Cascade reduces recoverability while preserving model utility.
arXiv:2608. 04519v1 Announce Type: new Abstract: Benchmarking machine unlearning methods is critical to understand whether sensitive knowledge is removed from large language models (LLMs) or not.
The paper introduces GRAPHSU, a graph‑guided selective unlearning method for language models that expands deletion beyond explicitly identified forget seeds. By constructing a weighted support‑route graph and propagating deletion pressure, GRAPHSU applies graded forgetting to high‑risk neighboring examples. Experiments on the TOFU and PISTOL benchmarks with GPT‑2 Medium and Llama‑3.2‑3B‑Instruct show that GRAPHSU achieves the lowest utility‑feasible soft leakage, reducing leakage by up to 49.5 percentage points compared to a seed‑only baseline.
arXiv:2608.29943v1 Announce Type: new Abstract: Large language models (LLMs) can memorize sensitive information, raising serious privacy concerns. Machine unlearning offers a potential solution to re...
arXiv:2610.31995v1 Announce Type: cross Abstract: As large language models (LLMs) face growing demands for data removal driven by regulatory compliance, copyright concerns, and privacy protection, ap...
CALIBURN is a new approach to large language model (LLM) unlearning that measures a model’s confidence in undesirable knowledge and uses this measure to fine‑tune unlearning gradient updates. By doing so, it offers more precise control over what is forgotten while better preserving the model’s overall utility. Experiments on benchmarks such as MUSE and WMDP show that CALIBURN outperforms existing methods in balancing knowledge removal with utility retention.
Benchmarking machine unlearning methods is critical to understand whether sensitive knowledge is removed from large language models (LLMs) or not. Current unlearning benchmarks include mainly single-hop questions and a narrow set of multi-hop questions.
Deep Contrastive Unlearning for Language Models (DeepCUT) is a framework that removes information from fine‑tuned language models by directly optimizing their latent space. It addresses the challenge of machine unlearning in black‑box models, which has been largely overlooked by previous work that only mitigated output effects. Experiments on real‑world datasets show that DeepCUT consistently outperforms baseline methods in both effectiveness and efficiency.
The paper introduces GONE, a benchmark for evaluating knowledge unlearning in large language models using structured knowledge graphs, and presents Neighborhood-Expanded Distribution Shaping (NEDS), a framework that leverages graph connectivity to separate forgotten facts from their semantic neighborhood. GONE disentangles direct fact removal, reasoning-based leakage, and catastrophic forgetting, while NEDS achieves high unlearning efficacy and locality on LLaMA-3-8B and Mistral-7B. The dataset is publicly available on Hugging Face.
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.
arXiv:2601. 09172v3 Announce Type: replace Abstract: As Large Language Models (LLMs) increasingly shape online content, removing targeted information from well-trained LLMs (also known as LLM unlearning) has become critical for web governance.
arXiv:2603. 11784v2 Announce Type: replace Abstract: As scaling laws push the training of frontier large language models (LLMs) toward ever-growing data requirements, training pipelines are approaching a regime where much of the publicly available online text may be consumed.
The paper introduces Propose-Then-Project Unlearning (PTP-U), a method for large language model unlearning that first weakens target knowledge associations and then projects non-target outputs back to the original distribution to recover capabilities. PTP-U aims to satisfy forgetting constraints while preserving fluent generation and performance on non-target tasks. Experiments on three benchmarks show PTP-U achieves a strong forgetting‑retention trade‑off, with 81.22%–91.03% forgetting and an average of 94.20% non‑target utility.