# Gender Trouble in Language Models: An Empirical Audit Guided by Gender Performativity Theory

arXiv: https://arxiv.org/abs/2505.14080 · HTML: https://mlsanity.com/paper/2505.14080/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 49 references that are in the map.
- First posted on arXiv 20 May 2025.

## Builds on (most cited first, 22 of 22)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!](https://mlsanity.com/paper/2310.03693/) (2023)
- [Language (Technology) is Power: A Critical Survey of "Bias" in NLP](https://mlsanity.com/paper/2005.14050/) (2020)
- [Bias and Fairness in Large Language Models: A Survey](https://mlsanity.com/paper/2309.00770/) (2023)
- [The Woman Worked as a Babysitter: On Biases in Language Generation](https://mlsanity.com/paper/1909.01326/) (2019)
- [Release Strategies and the Social Impacts of Language Models](https://mlsanity.com/paper/1908.09203/) (2019)
- [DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models](https://mlsanity.com/paper/2306.11698/) (2023)
- [Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus](https://mlsanity.com/paper/2104.08758/) (2021)
- [DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts](https://mlsanity.com/paper/2105.03023/) (2021)
- [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)
- [On Second Thought, Let's Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoning](https://mlsanity.com/paper/2212.08061/) (2022)
- [Theories of "Gender" in NLP Bias Research](https://mlsanity.com/paper/2205.02526/) (2022)
- ["I'm fully who I am": Towards Centering Transgender and Non-Binary Voices to Measure Biases in Open Language Generation](https://mlsanity.com/paper/2305.09941/) (2023)
- [WinoQueer: A Community-in-the-Loop Benchmark for Anti-LGBTQ+ Bias in Large Language Models](https://mlsanity.com/paper/2306.15087/) (2023)
- [Queer In AI: A Case Study in Community-Led Participatory AI](https://mlsanity.com/paper/2303.16972/) (2023)
- [Take and Took, Gaggle and Goose, Book and Read: Evaluating the Utility of Vector Differences for Lexical Relation Learning](https://mlsanity.com/paper/1509.01692/) (2015)
- [The Dark Side of Dataset Scaling: Evaluating Racial Classification in Multimodal Models](https://mlsanity.com/paper/2405.04623/) (2024)
- [Women Are Beautiful, Men Are Leaders: Gender Stereotypes in Machine Translation and Language Modeling](https://mlsanity.com/paper/2311.18711/) (2023)
- [The Root Shapes the Fruit: On the Persistence of Gender-Exclusive Harms in Aligned Language Models](https://mlsanity.com/paper/2411.03700/) (2024)
- [Language-Agnostic Bias Detection in Language Models with Bias Probing](https://mlsanity.com/paper/2305.13302/) (2023)

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

- [The AI's Poker Face: Contrasting Persuasion and Sycophancy in Voice-Based Multi-Turn Conversations](https://mlsanity.com/paper/2610.14124/) (2026)

## Abstract (arXiv)

Language models encode and subsequently perpetuate harmful gendered stereotypes. Research has succeeded in mitigating some of these harms, e.g. by dissociating non-gendered terms such as occupations from gendered terms such as 'woman' and 'man'. This approach, however, remains superficial given that associations are only one form of prejudice through which gendered harms arise. Critical scholarship on gender, such as gender performativity theory, emphasizes how harms often arise from the construction of gender itself, such as conflating gender with biological sex. In language models, these issues could lead to the erasure of transgender and gender diverse identities and cause harms in downstream applications, from misgendering users to misdiagnosing patients based on wrong assumptions about their anatomy. For FAccT research on gendered harms to go beyond superficial linguistic associations, we advocate for a broader definition of 'gender bias' in language models. We operationalize insights on the construction of gender through language from gender studies literature and then empirically test how 16 language models of different architectures, training datasets, and model sizes encode gender. We find that language models tend to encode gender as a binary category tied to biological sex, and that gendered terms that do not neatly fall into one of these binary categories are erased and pathologized. Finally, we show that larger models, which achieve better results on performance benchmarks, learn stronger associations between gender and sex, further reinforcing a narrow understanding of gender. Our findings lead us to call for a re-evaluation of how gendered harms in language models are defined and addressed.