Why Safety Probes Catch Liars But Miss Fanatics

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

arXiv:2606.24251v1 Announce Type: new Abstract: Large language models exhibit a growing range of misaligned behaviors such as strategic deception, sandbagging, and

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:2607.13075v1 Announce Type: cross Abstract: Context can change whether a request is harmful without changing its topic or surface form. We ask whether residual-stream probes

arXiv:2609.18515v1 Announce Type: new Abstract: Safety alignment teaches large language models (LLMs) to recognize harmful requests and reject risky instructions. Yet aligned

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:2604.04992v1 Announce Type: cross Abstract: Safety-aligned LLMs go through refusal training to reject harmful requests, but whether these mechanisms remain effective under