# Man Made Language Models? Evaluating LLMs' Perpetuation of Masculine Generics Bias

arXiv: https://arxiv.org/abs/2502.10577 · HTML: https://mlsanity.com/paper/2502.10577/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 73 references that are in the map.
- First posted on arXiv 14 Feb 2025.

## Builds on (most cited first, 20 of 20)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Enriching Word Vectors with Subword Information](https://mlsanity.com/paper/1607.04606/) (2016)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [CamemBERT: a Tasty French Language Model](https://mlsanity.com/paper/1911.03894/) (2019)
- [On LLMs-Driven Synthetic Data Generation, Curation, and Evaluation: A Survey](https://mlsanity.com/paper/2406.15126/) (2024)
- [Gender Bias in Neural Natural Language Processing](https://mlsanity.com/paper/1807.11714/) (2018)
- [Tower: An Open Multilingual Large Language Model for Translation-Related Tasks](https://mlsanity.com/paper/2402.17733/) (2024)
- [Counterfactual Data Augmentation for Mitigating Gender Stereotypes in Languages with Rich Morphology](https://mlsanity.com/paper/1906.04571/) (2019)
- [Gender Bias in Machine Translation](https://mlsanity.com/paper/2104.06001/) (2021)
- [NeuTral Rewriter: A Rule-Based and Neural Approach to Automatic Rewriting into Gender-Neutral Alternatives](https://mlsanity.com/paper/2109.06105/) (2021)
- [They, Them, Theirs: Rewriting with Gender-Neutral English](https://mlsanity.com/paper/2102.06788/) (2021)
- [Gender Bias in Large Language Models across Multiple Languages](https://mlsanity.com/paper/2403.00277/) (2024)
- [Are We in the AI-Generated Text World Already? Quantifying and Monitoring AIGT on Social Media](https://mlsanity.com/paper/2412.18148/) (2024)
- [The Rise of AI-Generated Content in Wikipedia](https://mlsanity.com/paper/2410.08044/) (2024)
- [Beyond Binary Gender Labels: Revealing Gender Biases in LLMs through Gender-Neutral Name Predictions](https://mlsanity.com/paper/2407.05271/) (2024)
- [Understanding the Impact of AI Generated Content on Social Media: The Pixiv Case](https://mlsanity.com/paper/2402.18463/) (2024)
- [Watching the Watchers: Exposing Gender Disparities in Machine Translation Quality Estimation](https://mlsanity.com/paper/2410.10995/) (2024)

## Built on by (most cited first, 1 of 1)

- [Personality Shapes Gender Bias in Persona-Conditioned LLM Narratives Across English and Hindi: An Empirical Investigation](https://mlsanity.com/paper/2604.23600/) (2026)

## Abstract (arXiv)

Instruct-based large language models (LLMs) have been shown to propagate and even amplify gender bias when prompted with contextually constrained instructions (e.g., writing a text from a description or selecting a gendered pronoun). However, little attention has been paid to biases in responses to contextually unconstrained (generic) instructions conveyed by gendered language, particularly masculine generics (MG). MG, found in many gender-marked languages, denote the use of the masculine gender as a supposedly neutral reference to mixed-gender groups or individuals whose gender is unknown or non-binary. Yet, psycholinguistic studies demonstrate that MG are not neutral and systematically induce gender bias. This study investigates how both local and proprietary LLMs are MG-biased when responding to generic prompts in French, examining LLMs' MG bias rates and use of gender-fair language (GFL). We create a 16k+ human noun database from existing lexical resources and evaluate six LLMs on four instruction-response datasets under two conditions: prompts with and without MG. Overall, we find that ≈27.57% of LLMs' responses to MG-filtered generic instructions are MG-biased (≈78.55% with MG-containing prompts). Moreover, we find that LLMs rarely use GFL spontaneously. These findings highlight the persistence of MG bias in LLM outputs and models' limited tendency towards GFL strategies.