超越匿名化的公平性？德语大语言模型生成简历中的人口统计信息泄露
Fairness Beyond Anonymization? Demographic Leakage in German LLM-Generated Resumes
- LMU Munich（慕尼黑大学）
- Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本研究审计德语LLM生成简历中的人口统计泄露，发现即使经匿名化和性别中性化处理，分类器仍能通过语义等价中性术语的细微差异区分性别，质疑匿名化公平干预的有效性。
AI中文摘要：
大语言模型（LLMs）正日益融入人工智能辅助招聘流程，包括自动化简历生成和筛选。根据欧盟《人工智能法案》，招聘领域被归类为高风险领域，使得公平性和透明性成为关键要求。现有工作主要聚焦于明确的招聘决策，而对生成的简历本身是否编码了可恢复的人口统计信息关注较少。在本研究中，我们对德语大语言模型生成的简历进行了两阶段的人口统计信息泄露审计。首先，我们使用ChatGPT（GPT-4o-mini）、Gemini 2.5 Flash-Lite以及多个规模的开源Qwen 3模型家族（4B、8B和14B），从真实的匿名化工作匹配档案中生成简历，系统性地改变与性别和种族相关的姓名，同时保持资质条件不变。其次，我们模拟下游简历筛选场景，即先对生成的简历进行匿名化和性别中性化处理，然后基于处理后的文本训练人口统计信息泄露分类器。我们发现，尽管采取了这些干预措施，分类器仍能可靠地区分使用男性和女性姓名生成的简历。这种泄露并非由明显的性别化措辞驱动，而是由德语中语义等价、形式上性别中性的术语使用上的细微差异所致。相比之下，与种族相关的泄露在各模型中相对较弱。我们的研究结果表明，看似中性的简历生成仍可能保留高度可预测的人口统计信号，这引发了人们对基于匿名化的公平性干预措施在多语言人工智能招聘流程中的有效性的担忧。
英文摘要：
Large language models (LLMs) are increasingly integrated into AI-assisted hiring pipelines, including automated resume generation and screening. Under the EU AI Act, the hiring domain is classified as high-risk, making fairness and transparency critical requirements. Existing work has primarily focused on explicit hiring decisions, while less attention has been paid to whether generated resumes themselves encode recoverable demographic information. In this work, we conduct a two-stage audit of demographic leakage in German-language LLM-generated resumes. First, we use ChatGPT (GPT-4o-mini), Gemini 2.5 Flash-Lite, and multiple scales of the open-weight Qwen 3 model family (4B, 8B, and 14B) to generate resumes from real anonymized job-matching profiles, systematically varying gender- and ethnicity-associated names while holding qualifications constant. Second, we simulate a downstream resume screening scenario, where the generated resumes are first anonymized and gender-neutralized, before demographic leakage classifiers are trained on the resulting texts. We find that, despite these interventions, classifiers reliably distinguish between resumes generated with male and female names. This leakage is not driven by overtly gendered wording, but by subtle differences in the usage of semantically equivalent, formally gender-neutral terms in German. In contrast, ethnicity-related leakage remains comparatively weak across models. Our findings demonstrate that apparently neutral resume generation can still preserve highly predictive demographic signals, raising concerns about anonymization-based fairness interventions in multilingual AI hiring pipelines.
