Is She Even Relevant? When BERT Ignores Explicit Gender Cues

• URL: http://arxiv.org/abs/2605.07622v1
• Date: Fri, 08 May 2026 11:48:22 GMT
• Title: Is She Even Relevant? When BERT Ignores Explicit Gender Cues
• Abstract summary: This paper investigates how and when gender information emerges in a Dutch BERT model trained from scratch.<n>It offers 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.
• Score: 0.962211505591938
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Uncertainty Quantification for Evaluating Machine Translation Bias [8.210153370613941]
  We use uncertainty to measure gender bias in machine translation systems.<n>We find that high translation accuracy does not correlate with exhibiting uncertainty appropriately, and that debiasing affects the two cases differently.
  arXiv  Detail & Related papers  (2025-07-24T12:10:21Z)
• Assumed Identities: Quantifying Gender Bias in Machine Translation of Gender-Ambiguous Occupational Terms [12.568906647547815]
  We introduce GRAPE, a probability-based metric designed to evaluate gender bias.<n>We present GAMBIT, a benchmarking dataset in English with gender-ambiguous occupational terms.<n>Using GRAPE, we evaluate several MT systems and examine whether their gendered translations in Greek and French align with or diverge from societal stereotypes.
  arXiv  Detail & Related papers  (2025-03-06T12:16:14Z)
• Beyond Binary Gender: Evaluating Gender-Inclusive Machine Translation with Ambiguous Attitude Words [85.48043537327258]
  Existing machine translation gender bias evaluations are primarily focused on male and female genders. This study presents a benchmark AmbGIMT (Gender-Inclusive Machine Translation with Ambiguous attitude words) We propose a novel process to evaluate gender bias based on the Emotional Attitude Score (EAS), which is used to quantify ambiguous attitude words.
  arXiv  Detail & Related papers  (2024-07-23T08:13:51Z)
• Leveraging Large Language Models to Measure Gender Representation Bias in Gendered Language Corpora [9.959039325564744]
  Large language models (LLMs) often inherit and amplify social biases embedded in their training data.<n>Gender bias is the association of specific roles or traits with a particular gender.<n>Gender representation bias is the unequal frequency of references to individuals of different genders.
  arXiv  Detail & Related papers  (2024-06-19T16:30:58Z)
• Multilingual Text-to-Image Generation Magnifies Gender Stereotypes and Prompt Engineering May Not Help You [64.74707085021858]
  We show that multilingual models suffer from significant gender biases just as monolingual models do.<n>We propose a novel benchmark, MAGBIG, intended to foster research on gender bias in multilingual models.<n>Our results show that not only do models exhibit strong gender biases but they also behave differently across languages.
  arXiv  Detail & Related papers  (2024-01-29T12:02:28Z)
• Probing Explicit and Implicit Gender Bias through LLM Conditional Text Generation [64.79319733514266]
  Large Language Models (LLMs) can generate biased and toxic responses. We propose a conditional text generation mechanism without the need for predefined gender phrases and stereotypes.
  arXiv  Detail & Related papers  (2023-11-01T05:31:46Z)
• How To Build Competitive Multi-gender Speech Translation Models For Controlling Speaker Gender Translation [21.125217707038356]
  When translating from notional gender languages into grammatical gender languages, the generated translation requires explicit gender assignments for various words, including those referring to the speaker. To avoid such biased and not inclusive behaviors, the gender assignment of speaker-related expressions should be guided by externally-provided metadata about the speaker's gender. This paper aims to achieve the same results by integrating the speaker's gender metadata into a single "multi-gender" neural ST model, easier to maintain.
  arXiv  Detail & Related papers  (2023-10-23T17:21:32Z)
• Will the Prince Get True Love's Kiss? On the Model Sensitivity to Gender Perturbation over Fairytale Texts [80.21033860436081]
  We investigate how models respond to gender stereotype perturbations through counterfactual data augmentation.<n>Our results show that models exhibit slight performance drops when faced with gender perturbations in the test set.<n>When fine-tuned on counterfactual training data, models become more robust to anti-stereotypical narratives.
  arXiv  Detail & Related papers  (2023-10-16T22:25:09Z)
• VisoGender: A dataset for benchmarking gender bias in image-text pronoun resolution [80.57383975987676]
  VisoGender is a novel dataset for benchmarking gender bias in vision-language models. We focus on occupation-related biases within a hegemonic system of binary gender, inspired by Winograd and Winogender schemas. We benchmark several state-of-the-art vision-language models and find that they demonstrate bias in resolving binary gender in complex scenes.
  arXiv  Detail & Related papers  (2023-06-21T17:59:51Z)
• The Birth of Bias: A case study on the evolution of gender bias in an English language model [1.6344851071810076]
  We use a relatively small language model, using the LSTM architecture trained on an English Wikipedia corpus. We find that the representation of gender is dynamic and identify different phases during training. We show that gender information is represented increasingly locally in the input embeddings of the model.
  arXiv  Detail & Related papers  (2022-07-21T00:59:04Z)
• Mitigating Gender Bias in Captioning Systems [56.25457065032423]
  Most captioning models learn gender bias, leading to high gender prediction errors, especially for women. We propose a new Guided Attention Image Captioning model (GAIC) which provides self-guidance on visual attention to encourage the model to capture correct gender visual evidence.
  arXiv  Detail & Related papers  (2020-06-15T12:16:19Z)
• Multi-Dimensional Gender Bias Classification [67.65551687580552]
  Machine learning models can inadvertently learn socially undesirable patterns when training on gender biased text. We propose a general framework that decomposes gender bias in text along several pragmatic and semantic dimensions. Using this fine-grained framework, we automatically annotate eight large scale datasets with gender information.
  arXiv  Detail & Related papers  (2020-05-01T21:23:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.