arXiv:2610.27555v1 Announce Type: cross Abstract: Safety pretraining has emerged as a promising paradigm for embedding safety deeply into a model during pretraining, yielding robustness to subsequent...
arXiv:2607. 02079v1 Announce Type: cross Abstract: We present HaloGuard 1.
arXiv:2606. 02530v1 Announce Type: new Abstract: Aligning Large Language Models (LLMs) with human values often degrades their general capabilities, termed the alignment tax.
arXiv:2610.07654v1 Announce Type: cross Abstract: On-policy distillation (OPD) has attracted growing attention as an effective way to transfer capabilities from teacher models to student models. Rece...
arXiv:2505. 18672v2 Announce Type: replace Abstract: Representation intervention aims to localize and modify the representations that encode the underlying concepts in large language models (LLMs) to elicit the aligned and expected behaviors.
The paper examines the vulnerability of open‑weight large language model safeguards that aim to block harmful usage by assuming new harmful behavior arises only through fine‑tuning. It demonstrates that simple, low‑cost attacks—abliteration and prefilling—can significantly increase attack success rates across multiple benchmarks, and proposes an abliteration‑resistant tuning (ART) method that mitigates these attacks. The study shows that safeguarding defenses must be evaluated against a broader range of attack strategies beyond fine‑tuning.
arXiv:2503. 11832v5 Announce Type: replace Abstract: Recent vision language models (VLMs) have made remarkable strides in generative modeling with multimodal inputs, particularly text and images.
arXiv:2607. 09697v1 Announce Type: new Abstract: Existing safety mechanisms for multimodal large language models (MLLMs) face a fundamental trade-off between safety and utility.
arXiv:2607. 01153v3 Announce Type: replace-cross Abstract: Safety evaluations for language models increasingly depend on judgments about ambiguous natural-language behaviour: whether a model followed an instruction, refused appropriately, complied with a policy, or misreported progress in an agentic task.
arXiv:2606. 00160v1 Announce Type: cross Abstract: Large language models (LLMs) suffer from degraded safety capabilities even when fine-tuned with benign datasets.
arXiv:2607. 15467v1 Announce Type: new Abstract: Knowledge distillation enables an adversary to replicate a proprietary classifier by querying its prediction interface and training a surrogate on the returned probability vectors.
arXiv:2608. 14089v1 Announce Type: new Abstract: Safety classifiers deployed with large language models often fail for two reasons: their decisions reflect the policy learned during training rather than the deployer's desired policy, and their performance degrades as deployment traffic evolves.