硅天花板：审计 GPT 在招聘中的种族与性别偏见
The Silicon Ceiling: Auditing GPT's Race and Gender Biases in Hiring
AI总结：
本研究受传统简历审计启发，对 OpenAI 的 GPT-3.5 在招聘中的种族与性别偏见进行 AI 审计，发现该模型在简历评估和生成中均表现出基于刻板印象的偏见。
摘要：
大型语言模型（LLMs）正越来越多地被引入工作场所，旨在提高效率和公平性。然而，人们对这些模型可能反映或加剧社会偏见和刻板印象产生了担忧。本研究探讨了 LLMs 对招聘实践的潜在影响。为此，受传统线下简历审计历史的启发，我们对一种常用的 LLM——OpenAI 的 GPT-3.5 中的种族和性别偏见进行了 AI 审计。我们使用具有不同种族和性别内涵的名字进行了两项研究：简历评估（研究 1）和简历生成（研究 2）。在研究 1 中，我们要求 GPT 对带有 32 个不同名字（2 种性别和 4 个种族群体的每种组合各 4 个名字）以及两个匿名选项的简历进行评分，涵盖 10 种职业和 3 项评估任务（总体评分、面试意愿和可雇佣性）。我们发现该模型反映了一些基于刻板印象的偏见。在研究 2 中，我们提示 GPT 为虚构的求职候选人创建简历（每个名字 10 份）。在生成简历时，GPT 暴露了潜在的偏见；女性的简历包含需要较少经验的职业，而亚洲人和西班牙裔的简历带有移民标志，如非母语英语以及非美国的教育和工作经历。我们的发现为日益增长的关于 LLM 偏见的文献，特别是在工作场所背景下，做出了贡献。
英文摘要：
Large language models (LLMs) are increasingly being introduced in workplace settings, with the goals of improving efficiency and fairness. However, concerns have arisen regarding these models' potential to reflect or exacerbate social biases and stereotypes. This study explores the potential impact of LLMs on hiring practices. To do so, we conduct an AI audit of race and gender biases in one commonly-used LLM, OpenAI's GPT-3.5, taking inspiration from the history of traditional offline resume audits. We conduct two studies using names with varied race and gender connotations: resume assessment (Study 1) and resume generation (Study 2). In Study 1, we ask GPT to score resumes with 32 different names (4 names for each combination of the 2 gender and 4 racial groups) and two anonymous options across 10 occupations and 3 evaluation tasks (overall rating, willingness to interview, and hireability). We find that the model reflects some biases based on stereotypes. In Study 2, we prompt GPT to create resumes (10 for each name) for fictitious job candidates. When generating resumes, GPT reveals underlying biases; women's resumes had occupations with less experience, while Asian and Hispanic resumes had immigrant markers, such as non-native English and non-U.S. education and work experiences. Our findings contribute to a growing body of literature on LLM biases, particularly in workplace contexts.
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。
