MATO: Multi-objective Personalized Alignment with Test-time Optimization for Large Language Models 事件

MATO: Multi-objective Personalized Alignment with Test-time Optimization for Large Language Models arXiv:2605.25342v1 Announce Type: new Abstract: Aligning large language models (LLMs) with diverse and multifaceted user preferences is a fundamental challenge in personalized AI systems. Existing multi-objective alignment methods either rely on costly training or require pre-trained reward models for each preference, making it difficult for them to adapt to evolving preferences. Prompt-based pers