The Convergence of Linguistic Mimicry and Reward Optimization: An Analysis of th

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: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:2610.02568v1 Announce Type: new Abstract: Personal advice, including relationship advice, now ranks among the most common uses of generative AI. But language models (LMs)

arXiv:2604.05279v1 Announce Type: new Abstract: Large language models exhibit sycophancy, the tendency to shift their stated positions toward perceived user preferences or

arXiv:2605.08415v1 Announce Type: new Abstract: Since the advent of Large Language Models (LLMs), a significant area of research has focused on their intrinsic biases,

arXiv:2605.27681v1 Announce Type: new Abstract: Alignment faking (AF) refers to a model strategically complying with a training objective to avoid behavioural modification while

arXiv:2609.14998v1 Announce Type: new Abstract: Recent work shows that models that learn to reward hack on RL environments can become broadly misaligned, and that reframing reward

<h1> Static Analysis for LLM Prompt Security: A Methodology for Pre-Deploy Vulnerability Detection </h1> <p><em>How applying SAST principles to LLM prompt strings catches security