Analyzing values about gendered language reform in LLMs' revisions

2025/05/27 by Jules Watson, Watson, Jules, Xi Wang +7
Social Sciences · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Gender Studies in Language

paper · pdf · doi:10.48550/arxiv.2505.21378

openalex publication_date 2025/05/27 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Within the common LLM use case of text revision, we study LLMs' revision of gendered role nouns (e.g., outdoorsperson/woman/man) and their justifications of such revisions. We evaluate their alignment with feminist and trans-inclusive language reforms for English. Drawing on insight from sociolinguistics, we further assess if LLMs are sensitive to the same contextual effects in the application of such reforms as people are, finding broad evidence of such effects. We discuss implications for value alignment.

Citations

• A trans linguistic perspective on multiple pronoun use in English
• Adapting Psycholinguistic Research for LLMs: Gender-inclusive Language in a Coreference Context
• Do language models practice what they preach? Examining language ideologies about gendered language reform encoded in LLMs
• AI generates covertly racist decisions about people based on their dialect
• From 'Showgirls' to 'Performers': Fine-tuning with Gender-inclusive Language for Bias Reduction in LLMs
• AboutMe: Using Self-Descriptions in Webpages to Document the Effects of English Pretraining Data Filters
• Misgendering and the health and wellbeing of nonbinary people in Canada
• Gender-Inclusive Grammatical Error Correction through Augmentation
• MISGENDERED: Limits of Large Language Models in Understanding Pronouns
• How Conservative are Language Models? Adapting to the Introduction of Gender-Neutral Pronouns
• Welcome to the Modern World of Pronouns: Identity-Inclusive Natural Language Processing beyond Gender
• NeuTral Rewriter: A Rule-Based and Neural Approach to Automatic\n Rewriting into Gender-Neutral Alternatives
• Language (Technology) is Power: A Critical Survey of "Bias" in NLP
• BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Related

• Do language models practice what they preach? Examining language ideologies about gendered language reform encoded in LLMs
• Adapting Psycholinguistic Research for LLMs: Gender-inclusive Language in a Coreference Context
• What an Elegant Bridge: Multilingual LLMs are Biased Similarly in Different Languages
• Man Made Language Models? Evaluating LLMs' Perpetuation of Masculine Generics Bias
• From 'Showgirls' to 'Performers': Fine-tuning with Gender-inclusive Language for Bias Reduction in LLMs