Zeyu Zhang, Xiangxiang Dai, Ziyi Han, Xutong Liu, John C. S. Lui

Steering Frozen LLMs: Adaptive Social Alignment via Online Prompt Routing

arXiv:2603.15647v1 Announce Type: new Abstract: Large language models (LLMs) are typically governed by post-training alignment (e.g., RLHF or DPO), which yields a largely static policy …