arXiv Machine Learning September 2, 2026 By Oren Rachmil, Avishag Shapira, Roy Betser, Omer Hofman, Itay Gershon, Asaf Shabtai, Yuval Elovici, Roman Vainshtein

Training-Free Policy Violation Detection via Activation-Space Whitening in LLMs

Read the original on arXiv Machine Learning →

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.

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 arXiv Machine Learning.

Hugging Face Trending Papers

Jun 24

PolicyAlign: Direct Policy-Based Safety Alignment for Large Language Models

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.

llms efficiency safety

arXiv Machine Learning

Jun 4

Few Tokens, Big Leverage: Preserving Safety Alignment by Constraining Safety Tokens during Fine-tuning

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.

By Guoli Wang, Haonan Shi, Tu Ouyang, An Wang

llms fine-tuning safety

arXiv AI

3d ago

PolicyMem: Geometric Policy Memory for LLM Governance

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...

By Yuanchen Bei, Zhengzhang Chen, Yanjun Zhao, Haoyu Wang, Hanghang Tong, Haifeng Chen

llms benchmarks safety

arXiv AI

Jun 16

CHILLGuard: Towards Fine-Grained Chinese LLM Safety Guardrail with Scalable Data Construction and Model-aware Preference Alignment

arXiv:2606. 15396v1 Announce Type: cross Abstract: Malicious content generated from large language models (LLMs) could pose severe safety risks and ethical concerns.

By Wenbo Yu, Bohua Wang, Hao Fang, Kuofeng Gao, Jingru Zeng, Xiaochen Yang, Tianyi Zhang, Xiaoxiao Ma, Jiawei Kong, Hao Wu, Bin Chen, Shu-Tao Xia, Min Zhang

llms rag benchmarks safety

arXiv AI

Aug 18

What Do Compliance Detectors Read? An Audit of Activation Probes and Guard Models

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.

By Saisab Sadhu, Aadit Sengupta, Vinay Kumar Sankarapu, Pratinav Seth

llms benchmarks

arXiv Machine Learning

Jun 10

Alignment Defends LLMs from Property Inference Attacks

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.

By Pengrun Huang, Chhavi Yadav, Ruihan Wu, Kamalika Chaudhuri

llms reinforcement-learning fine-tuning safety

One email a morning, machine-written

Related stories

PolicyAlign: Direct Policy-Based Safety Alignment for Large Language Models

Few Tokens, Big Leverage: Preserving Safety Alignment by Constraining Safety Tokens during Fine-tuning

PolicyMem: Geometric Policy Memory for LLM Governance

CHILLGuard: Towards Fine-Grained Chinese LLM Safety Guardrail with Scalable Data Construction and Model-aware Preference Alignment

What Do Compliance Detectors Read? An Audit of Activation Probes and Guard Models

Alignment Defends LLMs from Property Inference Attacks