arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2609.02092cs.AI

超越结果差距:面向基于大语言模型的多智能体决策系统的过程感知公平性诊断

Beyond Outcome Gaps: Process-Aware Fairness Diagnosis for LLM-based Multi-Agent Decision Systems

  • Nanjing University of Aeronautics and Astronautics(南京航空航天大学)
  • Collaborative Innovation Center of Novel Software Technology and Industrialization(新型软件技术与产业化协同创新中心)
  • Shandong University(山东大学)
  • School of Software Technology, Zhejiang University(浙江大学软件学院)
  • Ningbo Global Innovation Center, Zhejiang University(浙江大学宁波全球创新中心)

机构由 AI 辅助整理,请以论文原文为准。

Yiran Zhao, Lu Zhou, Liming Fang, Yufei Chen, Jiafei Wu, Zhe Liu, Xiaogang Xu

AI总结:

针对基于LLM的多智能体招聘决策系统,提出SCOPED-Hiring流程开展过程感知公平性诊断,发现结果平衡掩盖轨迹不公平,针对性修复可降负担且对招聘率影响极小。

AI中文摘要:

基于大语言模型(LLM)的多智能体系统(MAS)正日益被用于高风险决策,但基于结果的公平性审计可能会忽略决策轨迹内部风险产生的位置。我们提出SCOPED-Hiring,这是一种面向基于LLM的招聘MAS的过程感知公平性诊断流程。SCOPED-Hiring构建受控简历变体,运行基于角色的招聘委员会,记录超过31.1万条结构化决策轨迹,并将轨迹字段转换为由六个诊断维度组织的定量公平性信号:最终结果、反事实、过程、路径、动态和设计效应。SCOPED-Hiring揭示,平衡的最终招聘率可能掩盖多智能体决策轨迹中隐藏的轨迹不公平:职业差距引发怀疑、代理线索影响资质判断、身份线索导致调查不平等。基于这些诊断的针对性修复将总分层负担降低了72.3%,同时仅使招聘率变动1.86个百分点,表明过程诊断可指导有效修复。项目页面:this https URL

英文摘要:

LLM-based multi-agent systems (MAS) are increasingly considered for high-stakes decision-making, yet outcome-based fairness audits can miss where risks arise within the decision trajectory. We present SCOPED-Hiring, a process-aware fairness diagnosis pipeline for LLM-based hiring MAS. SCOPED-Hiring constructs controlled resume variants, runs role-based hiring committees, logs over 311K structured decision trajectories, and converts trajectory fields into quantitative fairness signals organized by six diagnostic lenses: final outcome, counterfactual, process, pathway, dynamic, and design effects. SCOPED-Hiring reveals that balanced final hire rates can mask hidden trajectory unfairness in multi-agent decision trajectories: career gaps trigger suspicion, proxy cues shape qualification judgments, and identity cues lead to unequal investigation. Targeted repair guided by these diagnoses reduces total layered burden by 72.3% while shifting the hire rate by only 1.86 pp, showing that process diagnosis can guide effective repair. Project Page: https://scoped-hiring-project-page.vercel.app/

补充信息

↑