Analyzing values about gendered language reform in LLMs' revisions
Jules Watson, Xi Wang, Raymond Liu, Suzanne Stevenson, Barend Beekhuizen
2025Year
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 transinclusive 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.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Builds on6
- Harms of Gender Exclusivity and Challenges in Non-Binary Representation in Language TechnologiesSunipa Dev, Masoud Monajatipoor, Anaelia Ovalle, Arjun Subramonian et al.EMNLP 2021 · 113 citations
- Adhering, Steering, and Queering: Treatment of Gender in Natural Language GenerationYolande A. A. Strengers, Lizhen Qu, Qiongkai Xu, Jarrod KnibbeCHI 2020 · 31 citations
- Toward Gender-Inclusive Coreference ResolutionYang Trista Cao, Hal Daumé IIIACL 2020 · 20 citations
- MISGENDERED: Limits of Large Language Models in Understanding PronounsTamanna Hossain, Sunipa Dev, Sameer SinghACL 2023 · 8 citations
- What social attitudes about gender does BERT encode? Leveraging insights from psycholinguisticsJulia Watson, Barend Beekhuizen, Suzanne StevensonACL 2023 · 5 citations
Related papers
- Job Unfair: An Investigation of Gender and Occupational Bias in Free-Form Text Completions by LLMsCamilla Casula, Sebastiano Vecellio Salto, Elisa Leonardelli, Sara TonelliEMNLP 2025
- The Lou Dataset - Exploring the Impact of Gender-Fair Language in German Text ClassificationAndreas Waldis, Joel Birrer, Anne Lauscher, Iryna GurevychEMNLP 2024 · 1 citation
- Measuring Bias or Measuring the Task: Understanding the Brittle Nature of LLM Gender BiasesBufan Gao, Elisa KreissEMNLP 2025 · 1 citation
- In-Context Impersonation Reveals Large Language Models' Strengths and BiasesLeonard Salewski, Stephan Alaniz, Isabel Rio-Torto, Eric Schulz et al.NeurIPS 2023 · 259 citations
- Adaptable Moral Stances of Large Language Models on Sexist Content: Implications for Society and Gender DiscourseRongchen Guo, Isar Nejadgholi, Hillary Dawkins, Kathleen C. Fraser et al.EMNLP 2024
