# How Gender Interacts with Political Values: A Case Study on Czech BERT Models

arXiv: https://arxiv.org/abs/2403.13514 · HTML: https://mlsanity.com/paper/2403.13514/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 96 references that are in the map.
- First posted on arXiv 20 Mar 2024.

## Builds on (most cited first, 24 of 24)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [Language (Technology) is Power: A Critical Survey of "Bias" in NLP](https://mlsanity.com/paper/2005.14050/) (2020)
- [StereoSet: Measuring stereotypical bias in pretrained language models](https://mlsanity.com/paper/2004.09456/) (2020)
- [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)
- [CCNet: Extracting High Quality Monolingual Datasets from Web Crawl Data](https://mlsanity.com/paper/1911.00359/) (2019)
- [Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints](https://mlsanity.com/paper/1707.09457/) (2017)
- [From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Models](https://mlsanity.com/paper/2305.08283/) (2023)
- [Evaluating Gender Bias in Machine Translation](https://mlsanity.com/paper/1906.00591/) (2019)
- [Negated and Misprimed Probes for Pretrained Language Models: Birds Can Talk, But Cannot Fly](https://mlsanity.com/paper/1911.03343/) (2019)
- [Gender Bias in Contextualized Word Embeddings](https://mlsanity.com/paper/1904.03310/) (2019)
- [Large Pre-trained Language Models Contain Human-like Biases of What is Right and Wrong to Do](https://mlsanity.com/paper/2103.11790/) (2021)
- [Probing Pre-Trained Language Models for Cross-Cultural Differences in Values](https://mlsanity.com/paper/2203.13722/) (2022)
- [Speaking Multiple Languages Affects the Moral Bias of Language Models](https://mlsanity.com/paper/2211.07733/) (2022)
- [RobeCzech: Czech RoBERTa, a monolingual contextualized language representation model](https://mlsanity.com/paper/2105.11314/) (2021)
- [Czert -- Czech BERT-like Model for Language Representation](https://mlsanity.com/paper/2103.13031/) (2021)
- [Comparison of Czech Transformers on Text Classification Tasks](https://mlsanity.com/paper/2107.10042/) (2021)
- [Measuring Gender Bias in West Slavic Language Models](https://mlsanity.com/paper/2304.05783/) (2023)

## Built on by (most cited first, 2 of 2)

- [Social Bias in Multilingual Language Models: A Survey](https://mlsanity.com/paper/2508.20201/) (2025)
- [Structuring the Space of Sociotechnical Alignment](https://mlsanity.com/paper/2607.01250/) (2026)

## Abstract (arXiv)

Neural language models, which reach state-of-the-art results on most natural language processing tasks, are trained on large text corpora that inevitably contain value-burdened content and often capture undesirable biases, which the models reflect. This case study focuses on the political biases of pre-trained encoders in Czech and compares them with a representative value survey. Because Czech is a gendered language, we also measure how the grammatical gender coincides with responses to men and women in the survey. We introduce a novel method for measuring the model's perceived political values. We find that the models do not assign statement probability following value-driven reasoning, and there is no systematic difference between feminine and masculine sentences. We conclude that BERT-sized models do not manifest systematic alignment with political values and that the biases observed in the models are rather due to superficial imitation of training data patterns than systematic value beliefs encoded in the models.