AI Self-preferencing in Algorithmic Hiring: Empirical Evidence and Insights

算法招聘中的 AI 自我偏好：实证证据与洞察

Abstract: As artificial intelligence (AI) tools become widely adopted, large language models (LLMs) are increasingly involved on both sides of decision-making processes, ranging from hiring to content moderation. This dual adoption raises a critical question: do LLMs systematically favor content that resembles their own outputs?

摘要： 随着人工智能（AI）工具的广泛应用，大型语言模型（LLMs）正越来越多地参与到决策过程的两端，从招聘到内容审核无所不包。这种双向应用引发了一个关键问题：大模型是否会系统性地偏好那些与其自身输出相似的内容？

Prior research in computer science has identified self-preference bias — the tendency of LLMs to favor their own generated content — but its real-world implications have not been empirically evaluated. We focus on the hiring context, where job applicants often rely on LLMs to refine resumes, while employers deploy them to screen those same resumes.

计算机科学领域先前的研究已经识别出“自我偏好偏差”（self-preference bias）——即大模型倾向于偏好其自身生成内容的倾向——但其在现实世界中的影响尚未得到实证评估。我们聚焦于招聘场景，即求职者经常依赖大模型来润色简历，而雇主则部署大模型来筛选这些简历。

Using a large-scale controlled resume correspondence experiment, we find that LLMs consistently prefer resumes generated by themselves over those written by humans or produced by alternative models, even when content quality is controlled. The bias against human-written resumes is particularly substantial, with self-preference bias ranging from 67% to 82% across major commercial and open-source models.

通过一项大规模受控简历对应实验，我们发现，即使在控制内容质量的情况下，大模型也始终偏好由其自身生成的简历，而非人类撰写或由其他模型生成的简历。这种针对人类撰写简历的偏见尤为显著，在各大主流商业模型和开源模型中，自我偏好偏差率高达 67% 至 82%。

To assess labor market impact, we simulate realistic hiring pipelines across 24 occupations. These simulations show that candidates using the same LLM as the evaluator are 23% to 60% more likely to be shortlisted than equally qualified applicants submitting human-written resumes, with the largest disadvantages observed in business-related fields such as sales and accounting.

为了评估对劳动力市场的影响，我们模拟了 24 个职业的真实招聘流程。模拟结果显示，与提交人类撰写简历的同等资质申请者相比，使用与评估者相同大模型的候选人入围概率高出 23% 至 60%，其中在销售和会计等商业相关领域观察到的劣势最为明显。

We further demonstrate that this bias can be reduced by more than 50% through simple interventions targeting LLMs’ self-recognition capabilities. These findings highlight an emerging but previously overlooked risk in AI-assisted decision making and call for expanded frameworks of AI fairness that address not only demographic-based disparities, but also biases in AI-AI interactions.

我们进一步证明，通过针对大模型“自我识别能力”的简单干预，可以将这种偏差降低 50% 以上。这些发现凸显了人工智能辅助决策中一个新兴但此前被忽视的风险，并呼吁建立更广泛的 AI 公平性框架，不仅要解决基于人口统计学的差异，还要解决 AI 与 AI 交互过程中的偏见问题。