大型语言模型 (LLMs) 越来越多地用于筛选和排名求职者,，从而激励候选人战略性地操纵算法招聘系统。我们研究自动 résumé 筛选, 中的提示注入，定义为微妙的自我推销文本，不引入新的资格，但旨在影响 LLM 评估。通过对照实验,，我们表明，当 résumé 质量均匀并且很少有候选人注入时，及时注入可以可靠地提高申请人排名。然而，随着越来越多的候选人注入,，, 的有效性迅速减弱，当操纵变得普遍时，, 就会崩溃。当候选人质量参差不齐, 时，平均而言，即时注入的效率较低,，但偶尔会导致质量较低的候选人排名高于质量较高的候选人,，从而引发公平性问题。总体而言，当操纵很少且候选人质量差异很小时，基于, LLM 的筛选最容易受到攻击。代码和资源可在:此 https URL 上公开获取
Large language models (LLMs) are increasingly used to screen and rank job applicants, creating incentives for candidates to strategically manipulate algorithmic hiring systems. We study prompt injection in automated résumé screening, defined as subtle self-promotional text that introduces no new qualifications but is designed to influence LLM evaluations. Using controlled experiments, we show that prompt injection reliably improves applicant rankings when résumé quality is homogeneous and few candidates inject. However, its effectiveness rapidly diminishes as more candidates inject, collapsing when manipulation becomes widespread. When candidate quality is heterogeneous, prompt injection is less effective on average, but can occasionally allow lower-quality candidates to outrank higher-quality ones, raising fairness concerns. Overall, LLM-based screening is most vulnerable when manipulation is rare and candidate quality differences are small. Code and resources are publicly available at: this https URL
科目:人工智能(cs.AI)
Subjects: Artificial Intelligence (cs.AI)