VC-Soup: Value-Consistency Guided Multi-Value Alignment for Large Language Models

ArXi:2603.18113v1 Announce Type: cross As large language models (LLMs) increasingly shape content generation, interaction, and decision-making across the Web, aligning them with human values has become a central objective in trustworthy AI. This challenge becomes even pronounced when aligning multiple, potentially conflicting human values. Although recent approaches, such as reward reweighting, prompt-based supervised fine-tuning, and model merging, attempt to tackle multi-value alignment, they still face two major limitations: (1.