谁会获得回电？生成式AI与性别偏见
Who Gets the Callback? Generative AI and Gender Bias
AI总结：
本文审计中等规模开源LLMs在招聘中的性别偏见，发现模型普遍青睐男性且与传统性别刻板印象高度一致，并证实宜人性较低的人设能减少偏见，揭示了AI招聘对劳动力市场公平性的潜在影响。
摘要：
生成式人工智能（AI），特别是大型语言模型（LLMs），正被迅速部署于招聘和候选人筛选中。我们使用包含332,044个真实在线招聘信息的数据集，对几个中等规模的开源LLMs进行了性别偏见审计。对于每条招聘信息，我们提示模型推荐资历相当的男性或女性候选人是否应获得面试回电。我们发现，大多数模型倾向于青睐男性，尤其是在高薪职位上。通过将职位描述映射到标准职业分类系统，我们发现在男性主导的职业中女性的回电率较低，而在女性关联的职业中回电率较高，这表明存在职业隔离。对招聘广告中语言特征的全面分析显示，模型推荐与传统性别刻板印象高度一致。为了考察招聘者身份的作用，我们通过注入大五人格特质并模拟历史人物的视角来引导模型行为。我们发现，宜人性较低的人设会减少刻板印象，这与LLMs中的宜人性偏见一致。我们的研究结果强调了AI驱动的招聘可能如何延续劳动力市场中的偏见，并对企业内部的公平性和多样性产生影响。
英文摘要：
Generative artificial intelligence (AI), particularly large language models (LLMs), is being rapidly deployed in recruitment and for candidate shortlisting. We audit several mid-sized open-source LLMs for gender bias using a dataset of 332,044 real-world online job postings. For each posting, we prompt the model to recommend whether an equally qualified male or female candidate should receive an interview callback. We find that most models tend to favor men, especially for higher-wage roles. Mapping job descriptions to the Standard Occupational Classification system, we find lower callback rates for women in male-dominated occupations and higher rates in female-associated ones, indicating occupational segregation. A comprehensive analysis of linguistic features in job ads reveals strong alignment of model recommendations with traditional gender stereotypes. To examine the role of recruiter identity, we steer model behavior by infusing Big Five personality traits and simulating the perspectives of historical figures. We find that less agreeable personas reduce stereotyping, consistent with an agreeableness bias in LLMs. Our findings highlight how AI-driven hiring may perpetuate biases in the labor market and have implications for fairness and diversity within firms.
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。
