Value Alignment Tax: Measuring Value Trade-offs in LLM Alignment
AI 摘要
提出Value Alignment Tax (VAT)框架,用于衡量对齐诱导的价值权衡和连锁反应。
主要贡献
- 提出了Value Alignment Tax (VAT)框架,量化对齐带来的价值权衡。
- 揭示了对齐过程中价值之间非均匀、结构化的联动关系。
- 强调了传统目标导向评估的局限性,指出了系统性的对齐风险。
方法论
构建基于Schwartz价值理论的场景-行为数据集,收集模型对齐前后规范判断,分析价值对齐效果。
原文摘要
Existing work on value alignment typically characterizes value relations statically, ignoring how interventions - such as prompting, fine-tuning, or preference optimization - reshape the broader value system. We introduce the Value Alignment Tax (VAT), a framework that measures how alignment-induced changes propagate across interconnected values relative to achieved on-target gain. VAT captures the dynamics of value expression under alignment pressure. Using a controlled scenario-action dataset grounded in Schwartz value theory, we collect paired pre-post normative judgments and analyze alignment effects across models, values, and alignment strategies. Our results show that alignment often produces uneven, structured co-movement among values. These effects are invisible under conventional target-only evaluation, revealing systemic, process-level alignment risks and offering new insights into the dynamics of value alignment in LLMs.