# Do language models practice what they preach? Examining language ideologies about gendered language reform encoded in LLMs

arXiv: https://arxiv.org/abs/2409.13852 · HTML: https://mlsanity.com/paper/2409.13852/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 67 references that are in the map.
- First posted on arXiv 20 Sep 2024.

## Builds on (most cited first, 28 of 28)

- [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)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [Language (Technology) is Power: A Critical Survey of "Bias" in NLP](https://mlsanity.com/paper/2005.14050/) (2020)
- [Large Language Models](https://mlsanity.com/paper/2307.05782/) (2023)
- [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)
- [Harms of Gender Exclusivity and Challenges in Non-Binary Representation in Language Technologies](https://mlsanity.com/paper/2108.12084/) (2021)
- [The Ghost in the Machine has an American accent: value conflict in GPT-3](https://mlsanity.com/paper/2203.07785/) (2022)
- [NLPositionality: Characterizing Design Biases of Datasets and Models](https://mlsanity.com/paper/2306.01943/) (2023)
- [Toward Gender-Inclusive Coreference Resolution](https://mlsanity.com/paper/1910.13913/) (2019)
- [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)
- [Welcome to the Modern World of Pronouns: Identity-Inclusive Natural Language Processing beyond Gender](https://mlsanity.com/paper/2202.11923/) (2022)
- [NeuTral Rewriter: A Rule-Based and Neural Approach to Automatic Rewriting into Gender-Neutral Alternatives](https://mlsanity.com/paper/2109.06105/) (2021)
- [MISGENDERED: Limits of Large Language Models in Understanding Pronouns](https://mlsanity.com/paper/2306.03950/) (2023)
- [Dialect prejudice predicts AI decisions about people's character, employability, and criminality](https://mlsanity.com/paper/2403.00742/) (2024)
- [AboutMe: Using Self-Descriptions in Webpages to Document the Effects of English Pretraining Data Filters](https://mlsanity.com/paper/2401.06408/) (2024)
- [Hi Guys or Hi Folks? Benchmarking Gender-Neutral Machine Translation with the GeNTE Corpus](https://mlsanity.com/paper/2310.05294/) (2023)
- [What about em? How Commercial Machine Translation Fails to Handle (Neo-)Pronouns](https://mlsanity.com/paper/2305.16051/) (2023)
- [How Conservative are Language Models? Adapting to the Introduction of Gender-Neutral Pronouns](https://mlsanity.com/paper/2204.10281/) (2022)
- [From 'Showgirls' to 'Performers': Fine-tuning with Gender-inclusive Language for Bias Reduction in LLMs](https://mlsanity.com/paper/2407.04434/) (2024)
- [Exploiting Biased Models to De-bias Text: A Gender-Fair Rewriting Model](https://mlsanity.com/paper/2305.11140/) (2023)
- [I am a Strange Dataset: Metalinguistic Tests for Language Models](https://mlsanity.com/paper/2401.05300/) (2024)
- [ELQA: A Corpus of Metalinguistic Questions and Answers about English](https://mlsanity.com/paper/2205.00395/) (2022)
- [Gender-Inclusive Grammatical Error Correction through Augmentation](https://mlsanity.com/paper/2306.07415/) (2023)
- [Test Suites Task: Evaluation of Gender Fairness in MT with MuST-SHE and INES](https://mlsanity.com/paper/2310.19345/) (2023)

## Built on by (most cited first, 5 of 5)

- [The PIMMUR Principles: Ensuring Validity in Collective Behavior of LLM Societies](https://mlsanity.com/paper/2509.18052/) (2025)
- [Structuring the Space of Sociotechnical Alignment](https://mlsanity.com/paper/2607.01250/) (2026)
- [Adapting Psycholinguistic Research for LLMs: Gender-inclusive Language in a Coreference Context](https://mlsanity.com/paper/2502.13120/) (2025)
- [Analyzing values about gendered language reform in LLMs' revisions](https://mlsanity.com/paper/2505.21378/) (2025)
- [Language Ideologies in a Multilingual Society: An LLM-based Analysis of Luxembourgish News Comments](https://mlsanity.com/paper/2604.27661/) (2026)

## Abstract (arXiv)

We study language ideologies in text produced by LLMs through a case study on English gendered language reform (related to role nouns like congressperson/-woman/-man, and singular they). First, we find political bias: when asked to use language that is "correct" or "natural", LLMs use language most similarly to when asked to align with conservative (vs. progressive) values. This shows how LLMs' metalinguistic preferences can implicitly communicate the language ideologies of a particular political group, even in seemingly non-political contexts. Second, we find LLMs exhibit internal inconsistency: LLMs use gender-neutral variants more often when more explicit metalinguistic context is provided. This shows how the language ideologies expressed in text produced by LLMs can vary, which may be unexpected to users. We discuss the broader implications of these findings for value alignment.