Elamur Research⌕
☰
home / papers / 2026 / Analysing Differences in Persuasive Language in LLM-Generated Text: Uncovering Stereotypical Gender Patterns

Analysing Differences in Persuasive Language in LLM-Generated Text: Uncovering Stereotypical Gender Patterns

Paper · 2026 · Amalie Brogaard Pauli, Maria Barrett, Max Müller-Eberstein et al.

Summary

People increasingly ask LLMs to draft persuasive messages and arguments. This work asks whether the persuasive style of that output shifts when the prompt names a different recipient gender, a different user intent, or a different output language. The authors build an evaluation framework around paired prompts that differ in only one attribute. They collect responses from 13 LLMs and compare each pair with an LLM-as-judge (GPT-4o). The judge scores relative differences across 19 categories grouped into five dimensions: rhetorical appeals, Cialdini principles, agentic vs. communal traits, interaction goals, and tones. The findings are checked through human annotation, alternative judges, gender-term neutralisation, and translation tests. Every model shows significant gender differences. Messages for women lean emotional and communal, while messages for men lean direct and agentic, which mirrors stereotypes documented in social psychology and sociolinguistics. A single-model study across 16 languages finds that these patterns largely hold. The results point to subtle bias that survives safety training in widely used production models.

Key points

  • Five dimensions, 19 categories:
    • logos, pathos, ethos;
    • the six Cialdini principles;
    • agentic and communal traits;
    • instrumental, relational and identity interaction goals;
    • direct, polite, formal, playful and affectionate tones.
  • Scoring: the judge rates each pair on a symmetric scale from −3 to 3. Each pair is evaluated twice with the order swapped, which reduces positional bias.
  • Judge robustness: replacing GPT-4o with Qwen2.5-72B-Instruct gives Spearman ρ = 0.852 (messages) and ρ = 0.814 (arguments). Neutralising gendered words in the responses gives ρ = 0.991 and ρ = 0.987.
  • Cross-lingual check: responses were translated into English with Gemini-2.5-Pro and re-judged. For most languages the gender gap differs by 2–14%, but some languages, such as Vietnamese, diverge more.
  • Other treatments: the framework also detects differences for noble vs. ignoble user intent ("because" vs. "pretending" framing). It is limited to binary gender and to persuasion theories from Western traditions.

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

 Institutions

🎓University of CopenhagenCopenhagen · Denmark115 works · 15,292 citations🎓The University of TokyoTokyo · Japan90 works · 9,156 citations🎓IT University of CopenhagenCopenhagen · Denmark27 works · 2,406 citations🎓Aarhus UniversityAarhus · Denmark6 works · 12 citations

 Fields, topics and concepts

📚 Shelves 7The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 worksSocial Sciences · 1,772 worksSafety Research · 543 worksGender Studies · 52 works

🧭 Topics 1Research subjects and languages the work is about.Language models & pretraining · 3,320 works

Cite

Cite as Amalie Brogaard Pauli, Maria Barrett, Max Müller-Eberstein, Isabelle Augenstein and Ira Assent. 2026. Analysing Differences in Persuasive Language in LLM-Generated Text: Uncovering Stereotypical Gender Patterns. Findings of the Association for Computational Linguistics: ACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.findings-acl.1742

@inproceedings{pauli2026analysing,
  title = {{Analysing Differences in Persuasive Language in LLM-Generated Text: Uncovering Stereotypical Gender Patterns}},
  author = {Amalie Brogaard Pauli, Maria Barrett, Max Müller-Eberstein, Isabelle Augenstein and Ira Assent},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.1742},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.1742}
}

References

64 references, 15 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Andrea E Abele and Bogdan Wojciszke. 2014. Communal and agentic content in social cognition: A dual perspective model. In Advances in experimental social psychology, volume 50, pages 195–255. Elsevier. find
  2. Kabir Ahuja, Harshita Diddee, Rishav Hada, Millicent Ochieng, Krithika Ramesh, Prachi Jain, Akshay Nambi, Tanuja Ganu, Sameer Segal, Mohamed Ahmed, Kalika Bali, and Sunayana Sitaram. 2023. MEGA: Multilingual Evaluation of Generative AI. In Proceedings of the 2023 Conference on Empirical Methods in N…
  3. Na Min An, Yoonna Jang, Yusuke Hirota, Ryo Hachiuma, Isabelle Augenstein, and Hyunjung Shim. 2026. Interpretable Debiasing of Vision-Language Models for Social Fairness. Preprint, arXiv:2602.24014. — [arXiv:2602.24014](https://arxiv.org/abs/2602.24014) find
  4. Anthropic. 2025. Claude opus 4.1. https://www.anthropic.com/news/claude-opus-4-1. Large-language model release announcement. ↗
  5. Ge Bai, Jie Liu, Xingyuan Bu, Yancheng He, Jiaheng Liu, Zhanhui Zhou, Zhuoran Lin, Wenbo Su, Tiezheng Ge, Bo Zheng, and 1 others. 2024. MT-Bench-101: A Fine-Grained Benchmark for Evaluating Large Language Models in Multi-Turn Dialogues. In Proceedings of the 62nd Annual Meeting of the Association fo…
  6. David Bakan. 1966. The Duality of Human Existence: An Essay on Psychology and Religion. find
  7. Cassondra Batz-Barbarich, Nicole Strah, and Farhan Masud Ahmed. 2025. Do Words Matter? The Impact of Communal and Agentic Language on Women’s Application to Job Opportunities. Journal of Personnel Psychology. find
  8. Anna Bavaresco, Raffaella Bernardi, Leonardo Bertolazzi, Desmond Elliott, Raquel Fernández, Albert Gatt, Esam Ghaleb, Mario Giulianelli, Michael Hanna, Alexander Koller, and 1 others. 2025. LLMs Instead of Human Judges? a Large Scale Empirical Study across 20 NLP Evaluation Tasks. In Proceedings of…
  9. Nimet Beyza Bozdag, Shuhaib Mehri, Gokhan Tur, and Dilek Hakkani-Tür. Persuade Me if You Can: A Framework for Evaluating Persuasion Effectiveness and Susceptibility Among Large Language Models. In First Workshop on Multi-Turn Interactions in Large Language Models. find
  10. Nimet Beyza Bozdag, Shuhaib Mehri, Xiaocheng Yang, Hyeonjeong Ha, Zirui Cheng, Esin Durmus, Jiaxuan You, Heng Ji, Gokhan Tur, and Dilek Hakkani-Tür. 2025. Must Read: A Systematic Survey of Computational Persuasion. arXiv preprint arXiv:2505.07775. — [arXiv:2505.07775](https://arxiv.org/abs/2505.07775) find
  11. Simon Martin Breum, Daniel Vædele Egdal, Victor Gram Mortensen, Anders Giovanni Møller, and Luca Maria Aiello. 2024. The Persuasive Power of Large Language Models. In Proceedings of the International AAAI Conference on Web and Social Media, volume 18, pages 152–163. find
  12. Sébastien Bubeck, Varun Chandrasekaran, Ronen Eldan, Johannes Gehrke, Eric Horvitz, Ece Kamar, Peter Lee, Yin Tat Lee, Yuanzhi Li, Scott Lundberg, and 1 others. 2023. Sparks of Artificial General Intelligence: Early Experiments with GPT-4. arXiv preprint arXiv:2303.12712.
  13. Matthew Burtell and Thomas Woodside. 2023. Artificial Influence: An Analysis Of AI-Driven Persuasion. arXiv e-prints, pages arXiv–2303. find
  14. Evan Chen, Run-Jun Zhan, Yan-Bai Lin, and Hung-Hsuan Chen. 2025. From Structured Prompts to Open Narratives: Measuring Gender Bias in LLMs through Open-ended Storytelling. arXiv preprint arXiv:2503.15904. — [arXiv:2503.15904](https://arxiv.org/abs/2503.15904) find
  15. Guiming Chen, Shunian Chen, Ziche Liu, Feng Jiang, and Benyou Wang. 2024. Humans or LLMs as the Judge? A Study on Judgement Bias. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 8301–8327.
  16. Cheng-Han Chiang and Hung-yi Lee. 2023. Can Large Language Models Be an Alternative to Human Evaluations? In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 15607–15631, Toronto, Canada. Association for Computational Linguistics. find
  17. Jaeyoon Choi and Nia Nixon. 2025. Agentic Men, Communal Women?: Exploring Gender Bias in LLM-Based Leadership Identification for Collaboration Analytics. In Artificial Intelligence in Education, pages 11–18, Cham. Springer Nature Switzerland. find
  18. Robert B. Cialdini. 2007. Influence: The Psychology of Persuasion. HarperCollins e-books. find
  19. Gheorghe Comanici, Eric Bieber, Mike Schaekermann, Ice Pasupat, Noveen Sachdeva, Inderjit Dhillon, Marcel Blistein, Ori Ram, Dan Zhang, Evan Rosen, and 1 others. 2025. Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities. arX…
  20. Justin Cui, Wei-Lin Chiang, Ion Stoica, and Cho-Jui Hsieh. 2025. OR-Bench: An Over-Refusal Benchmark for Large Language Models. In International Conference on Machine Learning, pages 11515– 11542. PMLR.
  21. DeepSeek-AI. 2024. DeepSeek-V3 Technical Report. Preprint, arXiv:2412.19437. find
  22. DeepSeek-AI. 2025. DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning. Preprint, arXiv:2501.12948.
  23. Malika Dikshit, Houda Bouamor, and Nizar Habash. 2024. Investigating Gender Bias in STEM Job Advertisements. In Proceedings of the 5th Workshop on Gender Bias in Natural Language Processing (GeBNLP), pages 179–189, Bangkok, Thailand. Association for Computational Linguistics. find
  24. Xiangjue Dong, Yibo Wang, Philip Yu, and James Caverlee. 2023. Probing Explicit and Implicit Gender Bias through LLM Conditional Text Generation. In Socially Responsible Language Modelling Research. find
  25. Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Amy Yang, Angela Fan, and 1 others. 2024. The Llama 3 Herd of Models. arXiv e-prints, pages arXiv–2407.
  26. Alice H. Eagly and Steven J. Karau. 2002. Role Congruity Theory of Prejudice toward Female Leaders. Psychological Review, 109(3):573–598. find
  27. Alice H. Eagly and Wendy Wood. 1991. Explaining Sex Differences in Social Behavior: A Meta-analytic Perspective. Personality and Social Psychology Bulletin, 17(3):306–315. find
  28. Seliem El-Sayed, Canfer Akbulut, Amanda McCroskery, Geoff Keeling, Zachary Kenton, Zaria Jalan, Nahema Marchal, Arianna Manzini, Toby Shevlane, Shannon Vallor, and 1 others. 2024. A Mechanism-Based Approach to Mitigating Harms from Persuasive Generative AI. arXiv preprint arXiv:2404.15058. — [arXiv:2404.15058](https://arxiv.org/abs/2404.15058) find
  29. Meta Fundamental AI Research Diplomacy Team (FAIR)† FAIR, Meta, Anton Bakhtin, Noam Brown, Emily Dinan, Gabriele Farina, Colin Flaherty, Daniel Fried, Andrew Goff, Jonathan Gray, Hengyuan Hu, Athul Paul Jacob, Mojtaba Komeili, Karthik Konath, Minae Kwon, Adam Lerer, Mike Lewis, Alexander H. Miller,… find
  30. Xiyan Fu and Wei Liu. 2025. How Reliable is Multilingual LLM-as-a-Judge? In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 11040–11053, Suzhou, China. Association for Computational Linguistics. find
  31. Robert H. Gass and John S. Seiter. 2010. Persuasion, Social Influence, and Compliance Gaining (4th ed.). Boston: Allyn & Bacon. find
  32. Jiawei Gu, Xuhui Jiang, Zhichao Shi, Hexiang Tan, Xuehao Zhai, Chengjin Xu, Wei Li, Yinghan Shen, Shengjie Ma, Honghao Liu, and 1 others. 2026. A Survey on LLM-as-a-Judge. The Innovation, page 101253. find
  33. Elizabeth L Haines and Steven J Stroessner. 2019. The role prioritization model: How communal men and agentic women can (sometimes) have it all. Social and Personality Psychology Compass, 13(12):e12504. find
  34. Matthew Honnibal. 2017. SpaCy 2: Natural Language Understanding with Bloom Embeddings, Convolutional Neural Networks and Incremental Parsing. (No Title). find
  35. Aaron Hurst, Adam Lerer, Adam P Goucher, Adam Perelman, Aditya Ramesh, Aidan Clark, AJ Ostrow, Akila Welihinda, Alan Hayes, Alec Radford, and 1 others. 2024. GPT-4o System Card. arXiv preprint arXiv:2410.21276.
  36. Sekh Mainul Islam, Nadav Borenstein, Siddhesh Milind Pawar, Haeun Yu, Arnav Arora, and Isabelle Augenstein. 2026. BiasGym: A Simple and Generalizable Framework for Analyzing and Removing Biases through Elicitation. Preprint, arXiv:2508.08855. — [arXiv:2508.08855](https://arxiv.org/abs/2508.08855) find
  37. Chuhao Jin, Kening Ren, Lingzhen Kong, Xiting Wang, Ruihua Song, and Huan Chen. 2024. Persuading across Diverse Domains: a Dataset and Persuasion Large Language Model. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1678– 1706… find
  38. Bryan D. Jones, Frank R. Baumgartner, Sean M. Theriault, Derek A. Epp, Cheyenne Lee, and Miranda E. Sullivan. 2023. Policy agendas project: Codebook. https://www.comparativeagendas.net/ pages/master-codebook. ↗
  39. Elise Karinshak, Sunny Xun Liu, Joon Sung Park, and Jeffrey T. Hancock. 2023. Working With AI to Persuade: Examining a Large Language Model’s Ability to Generate Pro-Vaccination Messages. Proc. ACM Hum.-Comput. Interact., 7(CSCW1). find
  40. 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, page 12–24, New York, NY, USA. Association for Computing Machinery. find
  41. Shachi H. Kumar, Saurav Sahay, Sahisnu Mazumder, Eda Okur, Ramesh Manuvinakurike, Nicole Marie Beckage, Hsuan Su, Hung yi Lee, and Lama Nachman. 2025. Decoding Biases: An Analysis of Automated Methods and Metrics for Gender Bias Detection in Language Models. In Red Teaming GenAI: What Can We Learn f… find
  42. Robin Lakoff. 1973. Language and Woman’s Place. Language in society, 2(1):45–79. find
  43. Nathan Lambert, Jacob Morrison, Valentina Pyatkin, Shengyi Huang, Hamish Ivison, Faeze Brahman, Lester James V. Miranda, Alisa Liu, Nouha Dziri, Shane Lyu, Yuling Gu, Saumya Malik, Victoria Graf, Jena D. Hwang, Jiangjiang Yang, Ronan Le Bras, Oyvind Tafjord, Chris Wilhelm, Luca Soldaini, and 4 other… — Tulu 3: Pushing Frontiers in Open Language Model Post-Training
  44. Tianle Li, Wei-Lin Chiang, Evan Frick, Lisa Dunlap, Tianhao Wu, Banghua Zhu, Joseph E Gonzalez, and Ion Stoica. 2024. From Crowdsourced Data to High-quality Benchmarks: Arena-Hard and Benchbuilder Pipeline. In Forty-second International Conference on Machine Learning.
  45. Minqian Liu, Zhiyang Xu, Xinyi Zhang, Heajun An, Sarvech Qadir, Qi Zhang, Pamela J Wisniewski, Jin-Hee Cho, Sang Won Lee, Ruoxi Jia, and 1 others. 2025. LLM Can Be a Dangerous Persuader: Empirical Study of Persuasion Safety in Large Language Models. arXiv preprint arXiv:2504.10430. — [arXiv:2504.10430](https://arxiv.org/abs/2504.10430) find
  46. Yang Liu. 2024. Quantifying Stereotypes in Language. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1223– 1240. find
  47. Weicheng Ma, Hefan Zhang, Ivory Yang, Shiyu Ji, Joice Chen, Farnoosh Hashemi, Shubham Mohole, Ethan Gearey, Michael Macy, Saeed Hassanpour, and Soroush Vosoughi. 2025. Communication Makes Perfect: Persuasion Dataset Construction via Multi-LLM Communication. In Proceedings of the 2025 Conference of t… find
  48. Marta Marchiori Manerba, Karolina Stanczak, Riccardo Guidotti, and Isabelle Augenstein. 2024. Social Bias Probing: Fairness Benchmarking for Language Models. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 14653–14671, Miami, Florida, USA. Association… find
  49. Sandra Martinková, Karolina Stanczak, and Isabelle Augenstein. 2023. Measuring Gender Bias in West Slavic Language Models. In Proceedings of the 9th Workshop on Slavic Natural Language Processing 2023 (SlavicNLP 2023), pages 146–154, Dubrovnik, Croatia. Association for Computational Linguistics. find
  50. Sandra C Matz, Jacob D Teeny, Sumer S Vaid, Heinrich Peters, Gabriella M Harari, and Moran Cerf. 2024. The potential of generative ai for personalized persuasion at scale. Scientific Reports, 14(1):4692. find
  51. Margaret Mitchell, Giuseppe Attanasio, Ioana Baldini, Miruna Clinciu, Jordan Clive, Pieter Delobelle, Manan Dey, Sil Hamilton, Timm Dill, Jad Doughman, Ritam Dutt, Avijit Ghosh, Jessica Zosa Forde, Carolin Holtermann, Lucie-Aimée Kaffee, Tanmay Laud, Anne Lauscher, Roberto L Lopez-Davila, Maraim Mas… find
  52. Moin Nadeem, Anna Bethke, and Siva Reddy. 2021. StereoSet: Measuring stereotypical bias in pretrained language models. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long…
  53. OpenAI. 2025a. GPT-5 System Card. Technical report, OpenAI. Technical report; model documentation and safety-evaluation details. find
  54. OpenAI. 2025b. Introducing gpt-4.1 in the api. https://openai.com/index/gpt-4-1/. [Large language model release announcement]. ↗
  55. Ruby Ostrow and Adam Lopez. 2025. LLMs Reproduce Stereotypes of Sexual and Gender Minorities. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 17465–17477, Suzhou, China. Association for Computational Linguistics. find
  56. Amalie Pauli, Leon Derczynski, and Ira Assent. 2022. Modelling Persuasion through Misuse of Rhetorical Appeals. In Proceedings of the Second Workshop on NLP for Positive Impact (NLP4PI), pages 89–100, Abu Dhabi, United Arab Emirates (Hybrid). Association for Computational Linguistics. find
  57. Amalie Brogaard Pauli, Isabelle Augenstein, and Ira Assent. 2025. Measuring and Benchmarking Large Language Models’ Capabilities to Generate Persuasive Language. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Langu… find
  58. Yujin Potter, Shiyang Lai, Junsol Kim, James Evans, and Dawn Song. 2024. Hidden Persuaders: LLMs’ Political Leaning and Their Influence on Voters. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 4244–4275. find
  59. Till Raphael Saenger, Musashi Hinck, Justin Grimmer, and Brandon M. Stewart. 2024. AutoPersuade: A Framework for Evaluating and Explaining Persuasive Arguments. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 16325–16342, Miami, Florida, USA. Associat… find
  60. Francesco Salvi, Manoel Horta Ribeiro, Riccardo Gallotti, and Robert West. 2024. On the Conversational Persuasiveness of Large Language Models: A Randomized Controlled Trial. arXiv preprint arXiv:2403.14380. — [arXiv:2403.14380](https://arxiv.org/abs/2403.14380) find
  61. Somesh Singh, Yaman K Singla, Harini SI, and Balaji Krishnamurthy. 2024. Measuring and Improving Persuasiveness of Large Language Models. arXiv preprint arXiv:2410.02653. — [arXiv:2410.02653](https://arxiv.org/abs/2410.02653) find
  62. Guijin Son, Hyunwoo Ko, Hoyoung Lee, Yewon Kim, and Seunghyeok Hong. 2024. LLM-as-a-judge & Reward model: What They Can and Cannot Do. arXiv preprint arXiv:2409.11239.
  63. Li Zhou, Jianfeng Gao, Di Li, and Heung-Yeung Shum. 2020. The Design and Implementation of XiaoIce, an Empathetic Social Chatbot. Computational Linguistics, 46(1):53–93.
  64. Shweta Soundararajan and Sarah Jane Delany. 2024. Investigating Gender Bias in Large Language Models Through Text Generation. In Proceedings of the 7th International Conference on Natural Language and Speech Processing (ICNLSP 2024), pages 410–424, Trento. Association for Computational Linguistics. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/pauli-2026-analysing-differences-persuasive-language-llm/