论文提出"活宪法"框架：主权模型的参与式对齐方法
Living constitutions: Participatory alignment for sovereign foundation models
主权国家或机构训自己的模型时，价值观不该照搬 Anthropic 的宪法。这篇把宪法起草设计成公民参与流程，还测了恶意参与者占比。做模型治理、政策研究或主权 AI 项目的人值得细看。
arXiv 论文 2611.13402 针对 Constitutional AI 中宪法由谁制定、如何决策等问题，提出把宪法起草视为类似公民科学的持续参与过程，并给出五项原则：迭代、模块化、可论证、情境性、正当性。
论文建议宪法条款标注为 settled、contested 或 underdetermined 三种状态，把持久分歧记录在案而非强行裁决，使文档能随时间和所覆盖人群保持响应性。
实证部分用基于智能体的建模验证：在 75% 参与者有善意的前提下，该流程可承受审议群体中 50% 的恶意行为者。作者指出，若无明确宪法，主权模型将默认遵循前沿模型厂商设定的规范。
Living constitutions: Participatory alignment for sovereign foundation models
In Constitutional AI, a plain-text "constitution" encodes values and gets incorporated into a model via post-training. However, the procedure for creating such a constitution poses significant challenges: who contributes, who decides which norms are included, and to what extent must the process be participatory or democratic? These challenges can be paralyzing. Yet, we argue that taking action is essential: without a deliberate constitution, sovereign models would risk misalignment or default to norms set by frontier model providers. We propose treating the development of a constitution as an evolving, participatory process akin to citizen science, iteratively drafted, tested, and refined. We therefore formulate five desirable principles: iterative, modular, justifiable, positional, and legitimate. We further argue that such a document must remain responsive not only over time but across the people it governs, and propose that provisions be marked as settled, contested, or underdetermined, so that durable disagreement is recorded in the constitution rather than resolved away. Empirically, we show via agent-based modelling that proposed process for maintaining living constitutions is robust against 50% bad actors among citizens - assuming a share of 75% participants with good intent in the deliberative body. This indicates that the proposed process tolerates a substantial share of adversarial participants.
This report is categorized under AITOP's "Papers" desk. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Constitutional AI, 模型对齐, 主权AI, 参与式设计.
Source attribution: curated from arXiv cs.AI (@Stine Lyngsø Beltoft, Jonas Vistrup, Peter Schneider-Kamp, Lukas Galke Poech).
