Safety interventions on dual-use knowledge typically choose between destroying hazardous content (e. g.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at Hugging Face Trending Papers.
arXiv:2607. 18639v1 Announce Type: new Abstract: Safety interventions on dual-use knowledge typically choose between destroying hazardous content (e.
arXiv:2608. 20338v1 Announce Type: new Abstract: Large Language Models (LLMs) increasingly require selective removal of harmful or sensitive knowledge, called unlearning, yet existing methods and benchmarks fail to evaluate this capability completely.
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.
EOPSA (Efficient On-Policy Self-Distilled Safety Alignment) addresses inefficiencies in On-Policy Self-Distillation (OPSD) for safety alignment by focusing training on safety-critical tokens. It introduces Adaptive Rollout Scheduling, which limits generation length based on a Teacher Rescue Rate metric, and Selective Distillation, which filters out safety-neutral tokens to concentrate gradient updates on safety-pivotal transitions. Experiments on models up to 32B parameters show that EOPSA reduces rollout computation by about 50% and backpropagates through only roughly 2% of tokens, outperforming full-token distillation baselines in safety compliance and reasoning retention.
arXiv:2607. 25063v1 Announce Type: new Abstract: Developers judge a model checkpoint by how it behaves.
arXiv:2606. 27683v1 Announce Type: cross Abstract: Edge devices increasingly invoke large language models (LLMs) through API services for context aware edge intelligence, while edge generated data may be collected to improve LLMs and may introduce sensitive, copyrighted, harmful, or outdated information into model behavior.