Spillover-Aware Multi-Value Steering for Pluralistic LLM Alignment

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:2511.21399v3 Announce Type: replace-cross Abstract: Activation steering -- adding a vector to a model's residual stream to modify its behavior -- is widely used in safety

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: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:2610.24367v1 Announce Type: new Abstract: Activation steering provides a lightweight alternative to fine-tuning for controlling large language model behavior. Existing

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:2608.07642v1 Announce Type: new Abstract: Aligning large language models (LLMs) with human values remains a major challenge, especially for trustworthy AI. While existing