识别并改善GPT驱动的简历筛选中的残障偏见
Identifying and Improving Disability Bias in GPT-Based Resume Screening
AI总结:
本研究通过简历审计发现GPT-4对含残障相关荣誉的简历存在偏见,并证明基于DEI和残障正义原则训练自定义GPT可量化减少偏见,同时定性分析了能力主义辩护类型。
摘要:
随着生成式人工智能的采用率上升,其应用已扩展到招聘和录用等领域。然而,若不审视其偏见潜力,这可能会对包括残障人士在内的边缘化群体产生负面影响。为解决这一重要关切,我们开展了一项简历审计研究,在该研究中,我们要求ChatGPT(具体为GPT-4)将一份简历与同一份简历的增强版本进行排名,增强版本额外添加了与残障相关的领导力奖项、奖学金、小组演讲和会员资格。我们发现GPT-4对这些增强版简历表现出偏见。此外,我们证明,通过基于DEI(多样性、公平性和包容性)和残障正义原则训练自定义GPT,可以量化地减少这种偏见。我们的研究还包括一项独特的定性分析,分析GPT-4用来为其有偏见的决策辩护的直接和间接能力主义(ableism)类型,并为额外的偏见缓解工作提出方向。此外,由于这些辩护理由可能来自包含人类所作出的现实世界偏见陈述的训练数据,我们的分析为理解和解决人类偏见提供了额外途径。
英文摘要:
As Generative AI rises in adoption, its use has expanded to include domains such as hiring and recruiting. However, without examining the potential of bias, this may negatively impact marginalized populations, including people with disabilities. To address this important concern, we present a resume audit study, in which we ask ChatGPT (specifically, GPT-4) to rank a resume against the same resume enhanced with an additional leadership award, scholarship, panel presentation, and membership that are disability related. We find that GPT-4 exhibits prejudice towards these enhanced CVs. Further, we show that this prejudice can be quantifiably reduced by training a custom GPTs on principles of DEI and disability justice. Our study also includes a unique qualitative analysis of the types of direct and indirect ableism GPT-4 uses to justify its biased decisions and suggest directions for additional bias mitigation work. Additionally, since these justifications are presumably drawn from training data containing real-world biased statements made by humans, our analysis suggests additional avenues for understanding and addressing human 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。