# Is She Even Relevant? When BERT Ignores Explicit Gender Cues

arXiv: https://arxiv.org/abs/2605.07622 · HTML: https://mlsanity.com/paper/2605.07622/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 32 of its 54 references that are in the map.
- First posted on arXiv 8 May 2026.

## Builds on (most cited first, 30 of 32)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Deep contextualized word representations](https://mlsanity.com/paper/1802.05365/) (2018)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [BERT Rediscovers the Classical NLP Pipeline](https://mlsanity.com/paper/1905.05950/) (2019)
- [StereoSet: Measuring stereotypical bias in pretrained language models](https://mlsanity.com/paper/2004.09456/) (2020)
- [Semantics derived automatically from language corpora contain human-like biases](https://mlsanity.com/paper/1608.07187/) (2016)
- [CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models](https://mlsanity.com/paper/2010.00133/) (2020)
- [Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods](https://mlsanity.com/paper/1804.06876/) (2018)
- [Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference](https://mlsanity.com/paper/2412.13663/) (2024)
- [The Woman Worked as a Babysitter: On Biases in Language Generation](https://mlsanity.com/paper/1909.01326/) (2019)
- [Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection](https://mlsanity.com/paper/2004.07667/) (2020)
- [Gender Bias in Coreference Resolution](https://mlsanity.com/paper/1804.09301/) (2018)
- [On Measuring Social Biases in Sentence Encoders](https://mlsanity.com/paper/1903.10561/) (2019)
- [Measuring Bias in Contextualized Word Representations](https://mlsanity.com/paper/1906.07337/) (2019)
- [Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve](https://mlsanity.com/paper/2309.13638/) (2023)
- [Assessing Social and Intersectional Biases in Contextualized Word Representations](https://mlsanity.com/paper/1911.01485/) (2019)
- [Debiasing Pre-trained Contextualised Embeddings](https://mlsanity.com/paper/2101.09523/) (2021)
- [Getting Gender Right in Neural Machine Translation](https://mlsanity.com/paper/1909.05088/) (2019)
- [Reducing Gender Bias in Neural Machine Translation as a Domain Adaptation Problem](https://mlsanity.com/paper/2004.04498/) (2020)
- [Unmasking Contextual Stereotypes: Measuring and Mitigating BERT's Gender Bias](https://mlsanity.com/paper/2010.14534/) (2020)
- [Machine Translationese: Effects of Algorithmic Bias on Linguistic Complexity in Machine Translation](https://mlsanity.com/paper/2102.00287/) (2021)
- [Lost in Translation: Loss and Decay of Linguistic Richness in Machine Translation](https://mlsanity.com/paper/1906.12068/) (2019)
- [Examining Gender Bias in Languages with Grammatical Gender](https://mlsanity.com/paper/1909.02224/) (2019)
- [EuroBERT: Scaling Multilingual Encoders for European Languages](https://mlsanity.com/paper/2503.05500/) (2025)
- [The Birth of Bias: A case study on the evolution of gender bias in an English language model](https://mlsanity.com/paper/2207.10245/) (2022)
- [NeoBERT: A Next-Generation BERT](https://mlsanity.com/paper/2502.19587/) (2025)
- [Evaluating Bias In Dutch Word Embeddings](https://mlsanity.com/paper/2011.00244/) (2020)
- [How does Grammatical Gender Affect Noun Representations in Gender-Marking Languages?](https://mlsanity.com/paper/1910.14161/) (2019)

## Abstract (arXiv)

Gender bias in large language models has primarily been investigated for English, while languages with grammatical or morphological gender remain comparatively understudied. This paper investigates how and when gender information emerges in a Dutch BERT model trained from scratch, offering one of the first checkpoint-level analyses of bias formation in a Transformer architecture for a language combining overt morphological gender marking and generic forms. By extracting contextual embeddings throughout training, we construct dynamic gender subspaces using linear SVMs to trace when gender becomes linearly encoded and how this encoding evolves over time. Contextual embeddings are often assumed to integrate contextual cues robustly, allowing models to adjust the representation of a word depending on its more local usage. We therefore test whether explicit gender cues in controlled sentence templates (e.g., Zij is een loodgieter ('She is a plumber')) can override learned statistical associations (plumber -> male). Our findings challenge this assumption: although gender becomes clearly linearly separable around epoch 20 and is distributed across multiple embedding dimensions, the model struggles to update its internal gender representation in light of explicit contextual cues in short sentence templates. Stereotypical gender-profession pairings are predicted far more accurately than anti-stereotypical ones, and generic forms in Dutch systematically default to a male interpretation, even when the context explicitly denotes a female referent. Together, our results seem to indicate that contextualization in the representations learned by our Dutch BERT model is not sufficiently dynamic along the probed gender direction: explicit gender cues in anti-stereotypical contexts are not reliably reflected in the resulting representations, resulting in persistent male-default behaviour.