大模型招聘时会被无关候选者误导，选更差的反而更倾向选好的。
Irrelevant Alternatives Bias Large Language Model Hiring Decisions
- 让大模型扮演招聘官，测试其是否受‘干扰项’影响。
- GPT-3.5和GPT-4均出现显著吸引力效应，好候选人被更青睐。
- 干扰项性别等无关属性会加剧偏见，适合关注AI公平性的研究者看。
我们研究大语言模型在招聘决策中是否存在人类常见的认知偏差——吸引力效应。该效应表现为：当存在一个劣质候选者时，会使一个更优候选者显得更具吸引力，从而提高其胜过非占优竞争者的概率。研究发现，当GPT-3.5和GPT-4扮演招聘官角色时，均表现出一致且显著的吸引力效应。干扰项的无关属性（如性别）会进一步放大该偏差。GPT-4的偏见波动幅度大于GPT-3.5。即使加入对干扰效应的警示或改变招聘官角色定义，结果依然稳健。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。