The paper introduces a training‑free approach to detect policy violations in large language models by treating the task as an out‑of‑distribution problem in the model’s activation space. It uses whitening‑inspired techniques to compute policy‑violation scores directly from normalized hidden activations, requiring only the policy text and a few illustrative examples. Experiments on several LLMs and policy benchmarks show the method achieves up to 86.0% F1, outperforming fine‑tuned and LLM‑as‑a‑judge baselines while being computationally lightweight.
Safety alignment of large language models (LLMs) typically depends on high-quality supervision data, such as safe demonstrations or preference pairs. However, in real-world deployment, emerging safety requirements are often specified as natural-language policies, while corresponding supervision data may be costly, delayed, or unavailable.
arXiv:2603. 07445v2 Announce Type: replace-cross Abstract: Large language models (LLMs) often require fine-tuning (FT) to perform well on downstream tasks, but FT can induce safety-alignment drift even when the training dataset contains only benign data.
arXiv:2609.13734v1 Announce Type: cross Abstract: As large language models (LLMs) are increasingly deployed in real-world high-stakes applications, effective governance has become essential. Existing...
arXiv:2606. 15396v1 Announce Type: cross Abstract: Malicious content generated from large language models (LLMs) could pose severe safety risks and ethical concerns.
arXiv:2608. 16852v1 Announce Type: new Abstract: Regulatory compliance monitoring in deployed language models is increasingly implemented as a legal and audit control, checking model outputs against written rules spanning data protection, healthcare, financial regulation, and platform policy.
arXiv:2606. 10217v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly fine-tuned on domain-specific datasets that may contain sensitive, dataset-level properties.
AdaGuard is an adaptive guard model that evaluates language‑model agent trajectories against user‑defined policies. The authors created the AdaptiveSafety dataset, containing 10,939 training and 1,000 test examples with policy rules, counterfactuals, explanations, and violated rules. Using supervised pre‑training followed by the SafePO reinforcement‑learning algorithm, they built 0.6B, 4B, and 8B guard models, with the 4B version achieving 89.30% accuracy on AdaptiveSafety and 71.82% on DynaBench.
arXiv:2607. 02072v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in domains requiring guardrails to detect unsafe, off-topic, or adversarial prompts.
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:2609.22094v1 Announce Type: cross Abstract: Content moderation systems traditionally entangle multimodal understanding with policy-specific classification, requiring full pipeline retraining fo...
arXiv:2606. 00686v1 Announce Type: new Abstract: The prevailing paradigm in large language model (LLM) alignment operates via erasure, filtering unsafe data or training models to strictly refuse harmful prompts.
TextCloak is a reinforcement‑learning driven framework that generates unlearnable examples (UEs) to protect textual data from unauthorized fine‑tuning of large language models (LLMs). It transforms clean text into perturbations that preserve meaning and naturalness while degrading the utility of models trained on them. Experiments on six datasets and nine LLMs show that TextCloak consistently impairs unauthorized fine‑tuning and remains robust across different architectures, training settings, and adaptive attacks.