Emergent Alignment

arXiv:2604.26167v1 Announce Type: cross Abstract: Recent work has shown that a model's input word embeddings can serve as effective control variables for steering its behavior

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

arXiv:2605.04454v1 Announce Type: new Abstract: Alignment evaluation in machine learning has largely become evaluation of models. Influential benchmarks score model outputs under

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:2605.00842v1 Announce Type: new Abstract: Emergent misalignment, where fine-tuning on narrow, non-harmful tasks induces harmful behaviors, poses a key challenge for AI

arXiv:2603.18113v1 Announce Type: cross Abstract: As large language models (LLMs) increasingly shape content generation, interaction, and decision-making across the Web, aligning

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