English(EN) Living constitutions: Participatory alignment for sovereign foundation models

AI对齐研究提出主权模型的参与式“活体宪法”

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-11 05:00

一篇新研究论文提出了一种用于对齐主权AI模型的“活体宪法”方法，建议采用一种参与式的、类似公民科学的过程来开发和完善模型的指导原则。该方法旨在确保模型与多元价值观对齐，而不是与前沿模型提供商的价值观对齐。所提出的框架强调迭代起草、模块化、理由说明、立场和合法性，并为已确定的、有争议的或未确定的规范提供了规定。基于智能体的建模表明，即使有相当一部分对抗性参与者，只要善意参与者占多数，该过程也是稳健的。 AI

影响提出了一种新颖的AI对齐框架，可能导致更民主化控制、偏见更少的AI系统。

排序理由提出AI对齐新方法的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 34 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 提出AI对齐新方法的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, safety; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Stine Lyngs{\o} Beltoft, Jonas Vistrup, Peter Schneider-Kamp, Lukas Galke Poech · 2026-11-11 05:00

活体宪法：主权基础模型的参与式对齐

arXiv:2611.13402v1 Announce Type: new Abstract: 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 decide…

本文如何被排名

报道来源 [1]

活体宪法：主权基础模型的参与式对齐

相关实体

相关话题