arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.15299cs.CYcs.AIcs.HC
收藏

无关选项偏差影响大型语言模型的招聘决策

Irrelevant Alternatives Bias Large Language Model Hiring Decisions

ETH Zurich(苏黎世联邦理工学院);The Adecco Group(德科集团)

Kremena Valkanova, Pencho Yordanov

AI总结:

该研究发现GPT-3.5和GPT-4在扮演招聘者时存在显著吸引效应(劣势候选人使优势候选人更具吸引力),诱饵无关属性(如性别)会放大偏差,且GPT-4偏差变异更大,警告和角色定义改变不影响结果稳健性。

摘要:

我们研究了大型语言模型(LLMs)在招聘决策中是否会表现出一种著名的人类认知偏差——吸引效应。吸引效应指的是,当存在一个劣势候选人时,优势候选人会变得更具吸引力,从而增加其被选中的可能性,超过一个非劣势的竞争者。我们的研究发现,当GPT-3.5和GPT-4扮演招聘者角色时,存在一致且显著的吸引效应证据。诱饵的无关属性(如性别)进一步放大了观察到的偏差。GPT-4比GPT-3.5表现出更大的偏差变异。即使包含针对诱饵效应的警告并改变招聘者角色定义,我们的发现仍然稳健。

英文摘要:

We investigate whether LLMs display a well-known human cognitive bias, the attraction effect, in hiring decisions. The attraction effect occurs when the presence of an inferior candidate makes a superior candidate more appealing, increasing the likelihood of the superior candidate being chosen over a non-dominated competitor. Our study finds consistent and significant evidence of the attraction effect in GPT-3.5 and GPT-4 when they assume the role of a recruiter. Irrelevant attributes of the decoy, such as its gender, further amplify the observed bias. GPT-4 exhibits greater bias variation than GPT-3.5. Our findings remain robust even when warnings against the decoy effect are included and the recruiter role definition is varied.

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。

↑