# Evaluating and Mitigating Gender Bias in Pre-trained Embeddings for ML-based Recruitment

arXiv: https://arxiv.org/abs/2607.20073 · HTML: https://mlsanity.com/paper/2607.20073/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 27 references that are in the map.
- First posted on arXiv 22 Jul 2026.

## Builds on (most cited first, 13 of 13)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers](https://mlsanity.com/paper/2002.10957/) (2020)
- [MPNet: Masked and Permuted Pre-training for Language Understanding](https://mlsanity.com/paper/2004.09297/) (2020)
- [Semantics derived automatically from language corpora contain human-like biases](https://mlsanity.com/paper/1608.07187/) (2016)
- [Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Setting](https://mlsanity.com/paper/1901.09451/) (2019)
- [Towards Understanding and Mitigating Social Biases in Language Models](https://mlsanity.com/paper/2106.13219/) (2021)
- [Learning Word Vectors for 157 Languages](https://mlsanity.com/paper/1802.06893/) (2018)
- [Demographic Bias in Biometrics: A Survey on an Emerging Challenge](https://mlsanity.com/paper/2003.02488/) (2020)
- [Human-Centric Multimodal Machine Learning: Recent Advances and Testbed on AI-based Recruitment](https://mlsanity.com/paper/2302.10908/) (2023)
- [Bias in Multimodal AI: Testbed for Fair Automatic Recruitment](https://mlsanity.com/paper/2004.07173/) (2020)
- [Addressing Bias in LLMs: Strategies and Application to Fair AI-based Recruitment](https://mlsanity.com/paper/2506.11880/) (2025)

## Abstract (arXiv)

AI-based recruitment systems that rely on machine learning models trained on historical CV data, risk perpetuating and amplifying social biases. A key challenge arises in unstructured CV text, where pre-trained language model embeddings may infer sensitive attributes such as gender even after explicit indicators are removed. In this paper, we evaluate nine pre-trained embedding models on the synthetic FairCVdb dataset, analyzing the informativeness of their embeddings for applicant scoring and their susceptibility to gender leakage, on both original and gender-scrubbed biographies. We further use a multi-task adversarial learning framework with gradient reversal to predict applicant suitability while suppressing gender information from learned representations. Finally, we use a multi-objective Pareto-front-based model selection to balance predictive utility and fairness. Our experimental results show that explicit gender scrubbing substantially reduces but does not eliminate gender leakage, while adversarial learning improves fairness mainly on original biographies and acts as a complementary strategy rather than a substitute for text-level debiasing.