Probing the Misaligned Thinking Process of Language Models

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:2603.25861v1 Announce Type: cross Abstract: Activation-based probes have emerged as a promising approach for detecting deceptively aligned AI systems by identifying internal

arXiv:2604.28031v1 Announce Type: cross Abstract: When researchers iteratively refine ideas with large language models, do the models preserve fidelity to the original objective?

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

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

arXiv:2605.00012v1 Announce Type: cross Abstract: Modern large language models (LLMs) are used in many business applications in general, and specifically in web search systems and

arXiv:2607.24758v1 Announce Type: new Abstract: Large language models are capable of recognizing evaluation contexts and altering their behavior to reflect evaluator expectations

<!-- 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