Consistency Without Alignment: Item-Sensitive Language Models Indistinguishable

arXiv:2604.22167v1 Announce Type: cross Abstract: Language models are increasingly capable and are being rapidly deployed on a population-level scale. As a result, the safety of

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

arXiv:2609.32035v1 Announce Type: new Abstract: Self-consistency assumes that independent samples disagree when a model is unsure, so agreement is evidence of correctness. Holding

arXiv:2604.19301v1 Announce Type: new Abstract: The conformity bias exhibited by large language models (LLMs) can pose a significant challenge to decision-making in LLM-based

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

arXiv:2605.15208v1 Announce Type: cross Abstract: Large Language Models are routinely compressed via post-training quantization to reduce inference costs and memory footprint for

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