arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2012.02394econ.GNcs.CYq-fin.EC
收藏

有偏见的程序员?有偏见的数据?实施AI伦理的现场实验

Biased Programmers? Or Biased Data? A Field Experiment in Operationalizing AI Ethics

Bo Cowgill, Fabrizio Dell'Acqua, Samuel Deng, Daniel Hsu, Nakul Verma, Augustin Chaintreau

摘要:

为什么会出现有偏见的预测?什么样的干预措施可以预防它们?我们评估了来自$\approx$ 400名AI工程师的820万个数学表现的算法预测,每个人都在随机分配的实验条件下开发了一个算法。我们的治疗组修改了程序员的激励措施、培训数据、意识和/或人工智能伦理的技术知识。然后,我们使用算法输入的随机审计操作和20 K受试者的地面真实数学表现来评估其算法的样本外预测。我们发现有偏差的预测主要是由有偏差的训练数据引起的。然而,更好的训练数据的三分之一的好处来自于一种新的经济机制:工程师在获得更好的训练数据时会付出更大的努力,对激励措施的反应也更快。我们还评估了程序员的人口统计学特征如何影响他们的表现,以及他们在关于性别和职业的内隐偏见(IAT)心理测试中的表现。我们没有发现任何证据表明,女性,少数民族和低IAT工程师表现出较低的偏见或歧视,在他们的代码。然而,我们确实发现预测误差在人口统计组内是相关的,这通过交叉人口统计平均来提高性能。最后,我们量化了实际管理或政策干预的好处和权衡,如技术建议,简单的提醒,以及减少算法偏差的改进激励措施。

英文摘要:

Why do biased predictions arise? What interventions can prevent them? We evaluate 8.2 million algorithmic predictions of math performance from $\approx$400 AI engineers, each of whom developed an algorithm under a randomly assigned experimental condition. Our treatment arms modified programmers' incentives, training data, awareness, and/or technical knowledge of AI ethics. We then assess out-of-sample predictions from their algorithms using randomized audit manipulations of algorithm inputs and ground-truth math performance for 20K subjects. We find that biased predictions are mostly caused by biased training data. However, one-third of the benefit of better training data comes through a novel economic mechanism: Engineers exert greater effort and are more responsive to incentives when given better training data. We also assess how performance varies with programmers' demographic characteristics, and their performance on a psychological test of implicit bias (IAT) concerning gender and careers. We find no evidence that female, minority and low-IAT engineers exhibit lower bias or discrimination in their code. However, we do find that prediction errors are correlated within demographic groups, which creates performance improvements through cross-demographic averaging. Finally, we quantify the benefits and tradeoffs of practical managerial or policy interventions such as technical advice, simple reminders, and improved incentives for decreasing algorithmic bias.

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。

↑