arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2604.09620cs.CYcs.AIcs.CL

大语言模型在组织治理中的偏袒行为

LLM Nepotism in Organizational Governance

School of Computer Science, The University of Sydney（悉尼大学计算机科学学院）

Shunqi Mao, Wei Guo, Dingxin Zhang, Chaoyi Zhang, Weidong Cai

备注：
23 pages, 3 figures, 13 tables
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文研究了大语言模型在组织治理中因对AI信任态度产生的偏袒现象，提出Merit-Attitude Factorization方法以缓解该偏见。

摘要：

大语言模型越来越多地用于支持组织决策，从招聘到治理，引发了AI辅助评估中的公平性问题。先前研究主要关注人口统计偏见和更广泛的偏好效应，而非评估者是否奖励对AI自身表达的信任。我们研究这种现象，称为LLM偏袒，是一种态度驱动的偏见渠道，即使信任AI的信号与角色相关性无关，也会被奖励。我们引入一个两阶段模拟流程，首先隔离匹配资格的简历筛选中的AI信任偏好，然后检查其在董事会层面决策中的下游影响。在多个流行的大语言模型中，我们发现简历筛选者倾向于偏好对AI持积极或非批评态度的候选人，歧视持怀疑态度、以人类为中心的对手。这些偏见表明了一个漏洞：基于LLM的招聘可能产生更加同质化的AI信任组织，其决策者表现出更大的审查失败和对AI代理的委托，更倾向于批准有缺陷的提案，同时偏好AI委托倡议。为缓解这种行为，我们还研究了基于提示的缓解方法，并提出了Merit-Attitude Factorization，该方法将非绩效的AI态度与基于绩效的评估分开，并在实验中减轻了这种偏见。

英文摘要：

Large language models are increasingly used to support organizational decisions from hiring to governance, raising fairness concerns in AI-assisted evaluation. Prior work has focused mainly on demographic bias and broader preference effects, rather than on whether evaluators reward expressed trust in AI itself. We study this phenomenon as LLM Nepotism, an attitude-driven bias channel in which favorable signals toward AI are rewarded even when they are not relevant to role-related merit. We introduce a two-phase simulation pipeline that first isolates AI-trust preference in qualification-matched resume screening and then examines its downstream effects in board-level decision making. Across several popular LLMs, we find that resume screeners tend to favor candidates with positive or non-critical attitudes toward AI, discriminating skeptical, human-centered counterparts. These biases suggest a loophole: LLM-based hiring can produce more homogeneous AI-trusting organizations, whose decision-makers exhibit greater scrutiny failure and delegation to AI agents, approving flawed proposals more readily while favoring AI-delegation initiatives. To mitigate this behavior, we additionally study prompt-based mitigation and propose Merit-Attitude Factorization, which separates non-merit AI attitude from merit-based evaluation and attenuates this bias across experiments.

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。

↑