arXiv Machine Learning
Jul 3
HaloGuard 1.0: An Open Weights Constitutional Classifier for Multilingual AI Safety
arXiv:2607. 02079v1 Announce Type: cross Abstract: We present HaloGuard 1.
A Reproducible, License-Aware Distillation Recipe for CPUDeployable Safety Classification
Related stories
arXiv AI
Jun 2
SafeSteer: Localized On-Policy Distillation for Efficient Safety Alignment
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 Machine Learning
Jul 24
Concept Concentration for Faithful Representation Intervention
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.
arXiv AI
Jun 2
Safety Mirage: How Spurious Correlations Undermine VLM Safety Fine-Tuning and Can Be Mitigated by Machine Unlearning
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 Machine Learning
Jul 14
Safe responses matter: Output-aware safety guardrail mitigate over-refusal in MLLMs
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 AI
Jul 31
Adversarial Pragmatics for AI Safety Evaluation: A Diagnostic Framework and Seed Benchmark for Language-Mediated Control
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 AI
Jun 2
DataShield: Safety-degrading Data Filtering for LLM Benign Instruction Fine-Tuning
arXiv:2606. 00160v1 Announce Type: cross Abstract: Large language models (LLMs) suffer from degraded safety capabilities even when fine-tuned with benign datasets.
arXiv Machine Learning
Jul 20
ADS-C: Antidistillation Sampling for Classification
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 AI
Aug 17
Regime-Conditional Verification: Correctness Estimation for Adapting and Monitoring Safety Classifiers
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.
arXiv AI
Jul 3
kNNGuard: Turning LLM Hidden Activations into a Training-Free Configurable Guardrail
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 AI
Aug 24
Trustworthy RAG: An Evaluation Agent for Detecting Misinformation and Knowledge Poisoning in Generative AI Systems
The paper introduces Trustworthy RAG, an evaluation agent designed to detect misinformation and knowledge poisoning in Retrieval-Augmented Generation systems. It combines natural language inference verification, a five-signal poison detector, and a weighted Trust Index to assess the reliability of retrieved content. Experiments on multiple LLMs show high accuracy and precision, with the agent effectively blocking unsafe advice in a secure-coding assistant scenario.
arXiv Machine Learning
Jun 2
Dialectics of Alignment: Harnessing Unsafe Knowledge for Dynamic Safety Routing
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.