Test-Time Safety Alignment

arXiv:2604.22117v1 Announce Type: cross Abstract: Aligned large language models(LLMs) remain vulnerable to adversarial manipulation, and their dependence on web-scale pretraining

arXiv:2604.18789v1 Announce Type: new Abstract: Reinforcement Learning from Human Feedback (RLHF) is central to aligning Large Language Models (LLMs), yet it introduces a critical

arXiv:2603.22829v1 Announce Type: new Abstract: With the rapid development and widespread application of Large Language Models (LLMs), their potential safety risks have attracted

arXiv:2603.25747v1 Announce Type: new Abstract: The rapid evolution of Large Multimodal Models (LMMs) has enabled agents to perform complex digital and physical tasks, yet their

arXiv:2605.11496v1 Announce Type: new Abstract: Recent published evidence from frontier laboratories shows that contemporary AI models can recognise evaluation contexts, latently

<!-- SC_OFF --><div class="md"><p>I set out to test whether AAVE-coded (African American English Vernacular) prompts cause MoE language models to route, deliberate, and respond

arXiv:2605.08496v1 Announce Type: new Abstract: Current adversarial robustness methods for large language models require extensive datasets of harmful prompts (thousands to

arXiv:2606.19527v1 Announce Type: new Abstract: Can Large Language Models (LLMs) discern when their own outputs are misaligned with human ethics? And can they self-correct? We