Elamur Research⌕
☰
home / papers / 2025 / Adapting Psycholinguistic Research for LLMs: Gender-inclusive Language in a Coreference Context

Adapting Psycholinguistic Research for LLMs: Gender-inclusive Language in a Coreference Context

Summary

The authors examine whether LLMs actually treat gender-inclusive formulations as neutral or still lean towards the masculine. To do so, they adapt to LLMs the psycholinguistic experiment of Tibblin et al. (2023), which was originally conducted in French. It uses pairs of sentences: the first mentions a group or an individual (the antecedent), and the second contains a coreferent word. The 44 French pairs were translated into English and German with ChatGPT and checked manually. They were then converted into templates into which masculine, feminine and neutral antecedents are inserted, and, for German, also various inclusive strategies. The models were evaluated in two ways: by the probability of a specific coreferent and by the gender in the generated continuations. In English, the models mostly preserve the gender of the antecedent but show a latent pull towards masculine forms and rarely use singular they. In German, the masculine bias outweighs all neutralization strategies. Nevertheless, inclusive forms do increase the probability of feminine and neutral referents. The paper shows how psycholinguistic methods help evaluate gender bias in models, particularly for languages with grammatical gender.

Key points

  • The data are built from the 44 templates of Tibblin et al. (2023). The English set has 13,464 plural examples (34 antecedent triplets; coreferents men/women/people) and 14,652 singular examples (37 triplets; he/she/they). The German set has 10,560 examples: 10 antecedents, each in eight inclusive variants.
  • The English antecedent triplets (such as swordsman–swordswoman–fencer) are taken from the resource of Bartl and Leavy (2024). The code and data are openly available in the GIL-coref-context repository on GitHub.
  • English singular: after a neutral antecedent, the most probable coreferent was he, not they. In the plural, after a feminine or neutral antecedent, the masculine coreferent ranks second in probability.
  • German: Männer always had a higher probability than Frauen or Personen, regardless of the inclusive strategy. At the same time, inclusive forms increase the share of feminine and neutral coreferents, which is consistent with the results of studies on humans.
  • Limitations: only models with 1.5–32 billion parameters were tested. Generation for German was evaluated only in a pilot setting: 160 sentence pairs were annotated by a single person, and in 23% of the continuations the model simply repeated the antecedent.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

Fields: Linguistics & languages

Topics: Coreference resolution

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2025.gebnlp-1.38 · arXiv 2502.13120

@inproceedings{bartl2025adapting,
  title = {{Adapting Psycholinguistic Research for LLMs: Gender-inclusive Language in a Coreference Context}},
  author = {Bartl, Marion and Murphy, Thomas Brendan and Leavy, Susan},
  booktitle = {Proceedings of the 6th Workshop on Gender Bias in Natural Language Processing (GeBNLP)},
  year = {2025},
  doi = {10.18653/v1/2025.gebnlp-1.38},
  eprint = {2502.13120},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.18653/v1/2025.gebnlp-1.38}
}

References

44 references, 5 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Chantal Amrhein, Florian Schottmann, Rico Sennrich, and Samuel Läubli. 2023. Exploiting Biased Models to De-bias Text: A Gender-Fair Rewriting Model. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 4486–4506, Toronto, Canada. Association for Computational Linguistics. find
  2. Marion Bartl and Susan Leavy. 2024. From ‘showgirls’ to ‘performers’: Fine-tuning with gender-inclusive language for bias reduction in LLMs. In Proceedings of the 5th Workshop on Gender Bias in Natural Language Processing (GeBNLP), pages 280–294, Bangkok, Thailand. Association for Computational Linguistics. find
  3. Connor Baumler and Rachel Rudinger. 2022. Recognition of They/Them as Singular Personal Pronouns in Coreference Resolution. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 3426–3432, Seattle, United States. Association for Computational Linguistics. ↗ our card
  4. Su Lin Blodgett, Solon Barocas, Hal Daumé III, and Hanna Wallach. 2020. Language (Technology) is Power: A Critical Survey of “Bias” in NLP. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 5454– 5476. find our card
  5. Stephanie Brandl, Ruixiang Cui, and Anders Søgaard. 2022. How Conservative are Language Models? Adapting to the Introduction of Gender-Neutral Pronouns. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 3624–3630, Seattle, United States. Association for Computational Linguistics. find
  6. Heather Burnett and Céline Pozniak. 2021. Political dimensions of gender inclusive writing in Parisian universities. Journal of Sociolinguistics, 25(5):808– 831. ↗
  7. Yang Trista Cao and Hal Daumé, III. 2021. Toward Gender-Inclusive Coreference Resolution: An Analysis of Gender and Bias Throughout the Machine Learning Lifecycle*. Computational Linguistics, 47(3):615–661. ↗ our card
  8. DeepSeek-AI. 2024. DeepSeek-V3 Technical Report. arXiv preprint. ArXiv:2412.19437 [cs]. ↗
  9. Sunipa Dev, Masoud Monajatipoor, Anaelia Ovalle, Arjun Subramonian, Jeff Phillips, and Kai-Wei Chang. 2021. Harms of Gender Exclusivity and Challenges in Non-Binary Representation in Language Technologies. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 1968–1994, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics. ↗
  10. Jacob Devlin, Ming-Wei Chang, Lee Kenton, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proceedings of NAACL-HLT, pages 4171–4186. find
  11. Anna-Katharina Dick, Matthias Drews, Valentin Pickard, and Victoria Pierz. 2024. GIL-GALaD: Gender Inclusive Language - German Auto-Assembled Large Database. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 7740–7745, Torino, Italia. ELRA and ICCL. Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 15789– 15809, Bangkok, Thailand. Association for Computational Linguistics. find
  12. Ramzi Fatfouta and Sabine Sczesny. 2023. Unconscious Bias in Job Titles: Implicit Associations Between Four Different Linguistic Forms with Women and Men. Sex Roles, 89(11):774–785. ↗
  13. Vipul Gupta, Pranav Narayanan Venkit, Shomir Wilson, and Rebecca Passonneau. 2024a. Sociodemographic Bias in Language Models: A Survey and Forward Path. In Proceedings of the 5th Workshop on Gender Bias in Natural Language Processing (GeBNLP), pages 295–322, Bangkok, Thailand. Association for Computational Linguistics. find
  14. Andy Field, Jeremy Miles, and Zoë Field. 2012. Discovering statistics using R. Sage publications. find
  15. Alice F. Freed. 2020. Women, Language and Public Discourse: Five decades of sexism and scrutiny. In Innovations and Challenges: Women, Language and Sexism. Routledge. Num Pages: 16. ↗
  16. David C. Funder and Daniel J. Ozer. 2019. Evaluating Effect Size in Psychological Research: Sense and Nonsense. Advances in Methods and Practices in Psychological Science, 2(2):156–168. Publisher: SAGE Publications Inc. ↗
  17. Vagrant Gautam, Eileen Bingert, Dawei Zhu, Anne Lauscher, and Dietrich Klakow. 2024. Robust pronoun fidelity with English LLMs: Are they reasoning, repeating, or just biased? Transactions of the Association for Computational Linguistics, 12:1755–1779. ↗
  18. Dirk Groeneveld, Iz Beltagy, Evan Walsh, Akshita Bhagia, Rodney Kinney, Oyvind Tafjord, Ananya Jha, Hamish Ivison, Ian Magnusson, Yizhong Wang, Shane Arora, David Atkinson, Russell Authur, Khyathi Chandu, Arman Cohan, Jennifer Dumas, Yanai Elazar, Yuling Gu, Jack Hessel, Tushar Khot, William Merrill, Jacob Morrison, Niklas Muennighoff, Aakanksha Naik, Crystal Nam, Matthew Peters, Valentina Pyatkin, Abhilasha Ravichander, Dustin Schwenk, Saurabh Shah, William Smith, Emma Strubell, Nishant Subramani, Mitchell Wortsman, Pradeep Dasigi, Nathan Lambert, Kyle Richardson, Luke Zettlemoyer, Jesse Dodge, Kyle Lo, Luca Soldaini, Noah Smith, and Hannaneh Hajishirzi. 2024a. OLMo: Accelerating the science of language models. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 15789–15809, Bangkok, Thailand. Association for Computational Linguistics. ↗
  19. Dirk Groeneveld, Iz Beltagy, Evan Walsh, Akshita Bhagia, Rodney Kinney, Oyvind Tafjord, Ananya Jha, Hamish Ivison, Ian Magnusson, Yizhong Wang, Shane Arora, David Atkinson, Russell Authur, Khyathi Chandu, Arman Cohan, Jennifer Dumas, Yanai Elazar, Yuling Gu, Jack Hessel, Tushar Khot, William Merrill, Jacob Morrison, Niklas Muennighoff, Aakanksha Naik, Crystal Nam, Matthew Peters, Valentina Pyatkin, Abhilasha Ravichander, Dustin Schwenk, Saurabh Shah, William Smith, Emma Strubell, Nishant Subramani, Mitchell Wortsman, Pradeep Dasigi, Nathan Lambert, Kyle Richardson, Luke Zettlemoyer, Jesse Dodge, Kyle Lo, Luca Soldaini, Noah Smith, and Hannaneh Hajishirzi. 2024b. OLMo: Accelerating the Science of Language Models. In Proceedings of the 62nd Annual Vipul Gupta, Pranav Narayanan Venkit, Shomir Wilson, and Rebecca Passonneau. 2024b. Sociodemographic bias in language models: A survey and forward path. In Proceedings of the 5th Workshop on Gender Bias in Natural Language Processing (GeBNLP), pages 295–322, Bangkok, Thailand. Association for Computational Linguistics. ↗
  20. Hadas Kotek, Rikker Dockum, and David Sun. 2023. Gender bias and stereotypes in Large Language Models. In Proceedings of The ACM Collective Intelligence Conference, CI ’23, pages 12–24, New York, NY, USA. Association for Computing Machinery. find
  21. J. Richard Landis and Gary G. Koch. 1977. The Measurement of Observer Agreement for Categorical Data. Biometrics, 33(1):159–174. Publisher: International Biometric Society. ↗
  22. Manuel Lardelli, Timm Dill, Giuseppe Attanasio, and Anne Lauscher. 2024a. Sparks of fairness: Preliminary evidence of commercial machine translation as English-to-German gender-fair dictionaries. In Proceedings of the 2nd International Workshop on Gender-Inclusive Translation Technologies, pages 12–21, Sheffield, United Kingdom. European Association for Machine Translation (EAMT). find
  23. Manuel Lardelli, Anne Lauscher, and Giuseppe Attanasio. 2024b. GeFMT: Gender-fair language in German machine translation. In Proceedings of the 25th Annual Conference of the European Association for Machine Translation (Volume 2), pages 37–38, Sheffield, UK. European Association for Machine Translation (EAMT). find
  24. Hector Levesque, Ernest Davis, and Leora Morgenstern. 2012. The winograd schema challenge. In Thirteenth International Conference on the Principles of Knowledge Representation and Reasoning. find
  25. Ruicheng Liu, Rui Mao, Anh Tuan Luu, and Erik Cambria. 2023. A brief survey on recent advances in coreference resolution. Artificial Intelligence Review, 56(12):14439–14481. ↗
  26. P. H. Matthews. 2014. The concise Oxford dictionary of linguistics, third;3rd; edition. Oxford University Press, Oxford. find
  27. Marta Mirabella, Claudia Mazzuca, Chiara De Livio, Bianca Di Giannantonio, Fau Rosati, Maric Martin Lorusso, Vittorio Lingiardi, Anna M. Borghi, and Guido Giovanardi. 2024. The Role of Language in Nonbinary Identity Construction: Gender Words Matter. Psychology of sexual orientation and gender diversity. Publisher: Educational Publishing Foundation. ↗
  28. Surya Monro. 2019. Non-binary and gen-derqueer: An overview of the field. International Journal of Transgenderism, 20(2-3):126– 131. Publisher: Taylor & Francis _eprint: https://doi.org/10.1080/15532739.2018.1538841. ↗
  29. Jane Noll, Mark Lowry, and Judith Bryant. 2018. Changes Over Time in the Comprehension of He and They as Epicene Pronouns. Journal of Psycholinguistic Research, 47(5):1057–1068. ↗
  30. Anaelia Ovalle, Palash Goyal, Jwala Dhamala, Zachary Jaggers, Kai-Wei Chang, Aram Galstyan, Richard Zemel, and Rahul Gupta. 2023. “I’m fully who I am”: Towards Centering Transgender and Non-Binary Voices to Measure Biases in Open Language Generation. In Proceedings of the 2023 ACM Conference on Fairness, Accountability, and Transparency, FAccT ’23, pages 1246–1266, New York, NY, USA. Association for Computing Machinery. find
  31. Brandon Papineau, Rob Podesva, and Judith Degen. 2022. ‘Sally the Congressperson’: The Role of Individual Ideology on the Processing and Production of English Gender-Neutral Role Nouns. Proceedings of the Annual Meeting of the Cognitive Science Society, 44(44). find
  32. Anne Pauwels. 2003. Linguistic Sexism and Feminist Linguistic Activism. In Janet Holmes and Miriam Meyerhoff, editors, The Handbook of Language and Gender, pages 550–570. Blackwell Publishing Ltd, Oxford, UK. ↗
  33. Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever. 2019. Language Models are Unsupervised Multitask Learners. find
  34. Rachel Rudinger, Jason Naradowsky, Brian Leonard, and Benjamin Van Durme. 2018. Gender Bias in Coreference Resolution. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pages 8–14, New Orleans, Louisiana. Association for Computational Linguistics. ↗ our card
  35. Sayaka Sato, Pascal Mark Gygax, Ute Gabriel, Jane Oakhill, and Lucie Escasain. 2025. Does Inclusive Language Increase the Visibility of Women, or Does It Simply Decrease the Visibility of Men? A Missing Piece of the Inclusive Language Jigsaw. Collabra: Psychology, 11(1):128470. find
  36. Dominic Schmitz, Viktoria Schneider, and Janina Esser. 2023. No genericity in sight: An exploration of the semantics of masculine generics in German. Glossa Psycholinguistics, 2(1). ↗
  37. Sabine Sczesny, Magda Formanowicz, and Franziska Moser. 2016. Can Gender-Fair Language Reduce Gender Stereotyping and Discrimination? Frontiers in Psychology, 7(Journal Article):25–25. Place: Switzerland Publisher: Frontiers Research Foundation. ↗
  38. Julia Tibblin, Jonas Granfeldt, Joost van de Weijer, and Pascal Gygax. 2023. The male bias can be attenuated in reading: on the resolution of anaphoric expressions following gender-fair forms in French. Glossa Psycholinguistics, 2(1). ↗
  39. Johanna Usinger and Philipp Müller. 2024. Geschickt gendern - das Genderwörterbuch. find
  40. Hellen P. Vergoossen, Philip Pärnamets, Emma A. Ren-ström, and Marie Gustafsson Sendén. 2020. Are New Gender-Neutral Pronouns Difficult to Process in Reading? The Case of Hen in SWEDISH. Frontiers in Psychology, 11. Publisher: Frontiers. find
  41. Julia Watson, Barend Beekhuizen, and Suzanne Stevenson. 2023. What social attitudes about gender does BERT encode? Leveraging insights from psycholinguistics. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6790–6809, Toronto, Canada. Association for Computational Linguistics. find
  42. Julia Watson, Sophia S. Lee, Barend Beekhuizen, and Suzanne Stevenson. 2025. Do language models practice what they preach? examining language ideologies about gendered language reform encoded in LLMs. In Proceedings of the 31st International Conference on Computational Linguistics, pages 1201– 1223, Abu Dhabi, UAE. Association for Computational Linguistics. find
  43. An Yang, Baosong Yang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Zhou, Chengpeng Li, Chengyuan Li, Dayiheng Liu, Fei Huang, Guanting Dong, Haoran Wei, Huan Lin, Jialong Tang, Jialin Wang, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Ma, Jianxin Yang, Jin Xu, Jingren Zhou, Jinze Bai, Jinzheng He, Junyang Lin, Kai Dang, Keming Lu, Keqin Chen, Kexin Yang, Mei Li, Mingfeng Xue, Na Ni, Pei Zhang, Peng Wang, Ru Peng, Rui Men, Ruize Gao, Runji Lin, Shijie Wang, Shuai Bai, Sinan Tan, Tianhang Zhu, Tianhao Li, Tianyu Liu, Wenbin Ge, Xiaodong Deng, Xiaohuan Zhou, Xingzhang Ren, Xinyu Zhang, Xipin Wei, Xuancheng Ren, Xuejing Liu, Yang Fan, Yang Yao, Yichang Zhang, Yu Wan, Yunfei Chu, Yuqiong Liu, Zeyu Cui, Zhenru Zhang, Zhifang Guo, and Zhihao Fan. 2024. Qwen2 Technical Report. arXiv preprint. ArXiv:2407.10671 [cs]. ↗
  44. Jieyu Zhao, Tianlu Wang, Mark Yatskar, Vicente Ordonez, and Kai-Wei Chang. 2018. Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pages 15–20, New Orleans, Louisiana. Association for Computational Linguistics. ↗ our card

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/papers/bartl-2025-adapting-psycholinguistic-research-llms-gender/