《负责任人工智能全球指数：2026年报告》
Global Index on Responsible AI: 2026 Report
AI总结：
该报告基于人权框架，通过多维度评估和大量数据收集，对各国负责任人工智能治理情况进行排名。发现治理虽在扩展，但转化为实际保护不足，尤其在算法公开等方面有欠缺，强调治理需向可执行保护等方向转变。
AI中文摘要：
基于诸如联合国教科文组织人工智能伦理建议等基于人权的框架，负责任人工智能全球指数（GIRAI）审视各国如何将负责任人工智能承诺转化为可执行的保护措施、机构能力和补救机制。GIRAI 2026从五个维度进行评估：包容与多样性、伦理与可持续性、劳动与技能、信任与安全以及人工智能在公共服务中的应用。135名国家层面的研究人员组成的全球网络收集并评估了38项指标的68138个数据点，这些指标分属三个支柱：政府人工智能政策与实施（17项指标）、民间社会参与（5项）、促成条件（15项）以及政府部署不可接受风险人工智能系统的记录案例。数据涵盖2023年11月至2025年9月。通过这些指标得出100分来对所有国家进行排名。研究结果显示，虽然负责任人工智能治理在扩展，135个国家中有126个在17项人工智能政策指标上至少有一项政府政策或举措，但这并不常转化为有意义的保护。例如，自第一版以来，全球南方国家占306个有框架指标新案例中的203个，但其中78%的框架仍无约束力，而全球北方为42%。政府对人工智能治理的承诺也未延伸至自身算法：透明度和可解释性是表现最强的指标，58%的国家有某种框架，但只有18%要求公开政府算法。在35个国家还发现了政府部署不可接受风险人工智能系统的可信证据。这些发现表明，负责任人工智能治理必须超越框架采用，转向基于权利的可执行保护、资源充足的监督机构和可及的补救措施。
英文摘要：
Grounded in human rights-based frameworks such as the UNESCO Recommendation on the Ethics of AI, the Global Index on Responsible AI (GIRAI) examines how countries translate responsible AI commitments into enforceable protections, institutional capacity, and redress mechanisms. GIRAI 2026 assesses these across five dimensions: Inclusion and Diversity, Ethics and Sustainability, Labour and Skills, Trust and Safety, and AI Use in Public Service. A global network of 135 country-level researchers collected and assessed 68,138 data points on 38 indicators organised across three pillars: government AI policy and implementation (17 indicators), civil society engagement (5), enabling conditions (15), and documented cases of government deployment of unacceptable-risk AI systems. The data covers November 2023 to September 2025. A score of 100 is derived from the indicators to rank all countries. Findings show that while responsible AI governance is expanding, with 126 of 135 countries having at least one government policy or initiative across the 17 AI Policy indicators, this does not often translate into meaningful protection. For instance, Global South countries account for 203 of 306 new cases of indicators with frameworks since the first edition, yet 78% of their frameworks remain non-binding compared with 42% in the Global North. Government commitment to AI governance also does not extend to their own algorithms: whereas Transparency and Explainability is one of the strongest performing indicators, with 58% of countries having some framework, only 18% require Public Disclosure of Government Algorithms. Credible evidence of government deployment of unacceptable-risk AI systems was also found in 35 countries. These findings show that responsible AI governance must move beyond framework adoption toward enforceable rights-based protections, resourced oversight institutions, and accessible redress.
