Emily和Greg仍比Lakisha和Jamal更易被录用吗？探究ChatGPT时代的算法招聘偏见
Are Emily and Greg Still More Employable than Lakisha and Jamal? Investigating Algorithmic Hiring Bias in the Era of ChatGPT
AI总结：
本研究复现经典招聘偏见实验，评估GPT-3.5、Bard等前沿大语言模型在简历匹配、简历摘要任务中的多维度偏见，发现其种族和性别维度表现稳健，怀孕状态、政治派别维度存在差异，并通过对比输入解码揭示偏见来源。
摘要：
GPT-3.5、Bard、Claude等大语言模型（LLM）可应用于众多任务，其中一个受关注的领域是算法招聘，具体为简历与职位类别的匹配，但这也引发了性别、种族、生育状况等受保护属性相关的偏见问题。Bertrand与Mullainathan（2004）的开创性研究通过田野实验确立了识别招聘偏见的黄金标准：对比仅在受保护属性（如带有种族暗示的名字，例如Emily或Lakisha）上有差异的相同简历的回复率。我们在GPT-3.5、Bard、Claude和Llama等前沿LLM上复现了该实验，评估其在性别、种族、生育状况、怀孕状态和政治派别方面的偏见（或无偏见情况）。我们在两项任务上评估LLM：（1）简历与职位类别匹配；（2）用就业相关信息总结简历。总体而言，LLM在种族和性别维度上表现稳健，在怀孕状态和政治派别维度上的表现存在差异。我们在开源LLM上使用对比输入解码，揭示了潜在的偏见来源。
英文摘要：
Large Language Models (LLMs) such as GPT-3.5, Bard, and Claude exhibit applicability across numerous tasks. One domain of interest is their use in algorithmic hiring, specifically in matching resumes with job categories. Yet, this introduces issues of bias on protected attributes like gender, race and maternity status. The seminal work of Bertrand & Mullainathan (2003) set the gold-standard for identifying hiring bias via field experiments where the response rate for identical resumes that differ only in protected attributes, e.g., racially suggestive names such as Emily or Lakisha, is compared. We replicate this experiment on state-of-art LLMs (GPT-3.5, Bard, Claude and Llama) to evaluate bias (or lack thereof) on gender, race, maternity status, pregnancy status, and political affiliation. We evaluate LLMs on two tasks: (1) matching resumes to job categories; and (2) summarizing resumes with employment relevant information. Overall, LLMs are robust across race and gender. They differ in their performance on pregnancy status and political affiliation. We use contrastive input decoding on open-source LLMs to uncover potential sources of 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。
