# Fairness Beyond Anonymization? Demographic Leakage in German LLM-Generated Resumes

arXiv: https://arxiv.org/abs/2609.22188 · HTML: https://mlsanity.com/paper/2609.22188/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 27 references that are in the map.
- First posted on arXiv 28 Aug 2026.

## Builds on (most cited first, 8 of 8)

- [Fairness and Bias in Algorithmic Hiring: a Multidisciplinary Survey](https://mlsanity.com/paper/2309.13933/) (2023)
- [The Silicon Ceiling: Auditing GPT's Race and Gender Biases in Hiring](https://mlsanity.com/paper/2405.04412/) (2024)
- [Auditing the Use of Language Models to Guide Hiring Decisions](https://mlsanity.com/paper/2404.03086/) (2024)
- [AI Hiring with LLMs: A Context-Aware and Explainable Multi-Agent Framework for Resume Screening](https://mlsanity.com/paper/2504.02870/) (2025)
- [BAD: BiAs Detection for Large Language Models in the context of candidate screening](https://mlsanity.com/paper/2305.10407/) (2023)
- [Fairness in AI-Driven Recruitment: Challenges, Metrics, Methods, and Future Directions](https://mlsanity.com/paper/2405.19699/) (2024)
- [Small Changes, Big Impact: Demographic Bias in LLM-Based Hiring Through Subtle Sociocultural Markers in Anonymised Resumes](https://mlsanity.com/paper/2603.05189/) (2026)
- [Synthetic CVs To Build and Test Fairness-Aware Hiring Tools](https://mlsanity.com/paper/2508.21179/) (2025)

## Abstract (arXiv)

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.