arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.13246cs.CYcs.AI
收藏

全球人工智能偏见审计用于技术治理

Global AI Bias Audit for Technical Governance

Apart Research(阿帕特研究机构)

Jason Hung

AI总结:

本文通过全球人工智能数据集对Llama-3 8B模型进行压力测试,揭示了全球南北在人工智能技术知识和信息获取上的显著差距,呼吁更包容的数据表示以促进全球AI治理。

摘要:

本文呈现了对大型语言模型(LLMs)项目全球审计的探索阶段的输出。在这一探索阶段,我以全球人工智能数据集(GAID)项目为框架,对Llama-3 8B模型进行压力测试,并评估技术人工智能治理意识中的地理和社会经济偏见。通过使用来自213个国家和八个技术指标的1704个查询对模型进行压力测试,我识别出一个显著的数字障碍和差距,将全球北半球与南半球分隔开来。结果表明,模型只能在11.4%的查询回答中提供数字/事实响应,而这些响应的经验有效性尚未得到验证。发现揭示了人工智能的技术知识在高收入地区高度集中,而来自全球南半球的低收入国家则面临不成比例的系统信息缺口。这种北半球与南半球之间的差异对全球人工智能安全和包容性治理构成了令人担忧的风险,因为欠发达地区的政策制定者可能缺乏可靠的基于数据的洞察力,或可能被幻觉事实所误导。本文结论指出,当前的人工智能对齐和训练过程加剧了现有的地缘经济和地缘政治不对称,呼吁需要更加包容的数据表示,以确保人工智能成为真正全球性的资源。

英文摘要:

This paper presents the outputs of the exploratory phase of a global audit of Large Language Models (LLMs) project. In this exploratory phase, I used the Global AI Dataset (GAID) Project as a framework to stress-test the Llama-3 8B model and evaluate geographic and socioeconomic biases in technical AI governance awareness. By stress-testing the model with 1,704 queries across 213 countries and eight technical metrics, I identified a significant digital barrier and gap separating the Global North and South. The results indicate that the model was only able to provide number/fact responses in 11.4% of its query answers, where the empirical validity of such responses was yet to be verified. The findings reveal that AI's technical knowledge is heavily concentrated in higher-income regions, while lower-income countries from the Global South are subject to disproportionate systemic information gaps. This disparity between the Global North and South poses concerning risks for global AI safety and inclusive governance, as policymakers in underserved regions may lack reliable data-driven insights or be misled by hallucinated facts. This paper concludes that current AI alignment and training processes reinforce existing geoeconomic and geopolitical asymmetries, and urges the need for more inclusive data representation to ensure AI serves as a truly global resource.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑