Arbitrary Cipher Attacks Against Large Language Models Do Not Require Fine-Tunin

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:2605.21706v1 Announce Type: new Abstract: Safety-aligned language models are trained to refuse harmful requests, yet refusal behavior can be suppressed by steering their

arXiv:2603.18908v1 Announce Type: new Abstract: Language models increasingly appear to learn similar representations, despite differences in training objectives, architectures,

arXiv:2604.08557v1 Announce Type: cross Abstract: Diffusion-based language models (dLLMs) generate text by iteratively denoising masked token sequences. We show that their safety

arXiv:2609.04665v1 Announce Type: new Abstract: Self-evolving language models improve by proposing candidate updates and keeping whatever raises a visible score. When that score

<!-- 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:2608.27512v1 Announce Type: cross Abstract: Post-training quantization is often treated as a semantically neutral optimization for edge deployment of Large Language Models.

arXiv:2604.13206v1 Announce Type: new Abstract: As Large Language Models (LLMs) are increasingly integrated into agentic workflows, their unpredictability stemming from numerical