用AI倾听不同风格的人，公平评估真实技能
Equitable Evaluation via Elicitation
- 设计交互式AI系统，通过对话挖掘技能，不依赖自我陈述
- 实验证明该方法可降低自述风格对评估偏差的影响
- 适合招聘平台、组织重组等需公平评估的场景
能力相当的求职者可能因表达风格差异（如自夸或低调）导致评估不公。本文构建一个交互式AI技能挖掘系统，在保留个人表达方式的同时准确判断技能水平。系统可用于新用户加入职业网络平台或企业重组时的人员匹配。为获取训练数据，训练大模型模拟虚拟人类进行互动。该方法能缓解个体自述带来的内生性偏差，并通过数学上严格的公平性约束，确保表达风格与评估误差之间的协方差极小，实现更公正的技能评估。
原文摘要 · Abstract (English)
Individuals with similar qualifications and skills may vary in their demeanor, or outward manner: some tend toward self-promotion while others are modest to the point of omitting crucial information. Comparing the self-descriptions of equally qualified job-seekers with different self-presentation styles is therefore problematic. We build an interactive AI for skill elicitation that provides accurate determination of skills while simultaneously allowing individuals to speak in their own voice. Such a system can be deployed, for example, when a new user joins a professional networking platform, or when matching employees to needs during a company reorganization. To obtain sufficient training data, we train an LLM to act as synthetic humans. Elicitation mitigates endogenous bias arising from individuals' own self-reports. To address systematic model bias we enforce a mathematically rigorous notion of equitability ensuring that the covariance between self-presentation manner and skill evaluation error is small.
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。