Elamur Research⌕
☰
home / papers / 2026 / German General Social Survey Personas: A Survey-Derived Persona Prompt Collection for Population-Aligned LLM Studies

German General Social Survey Personas: A Survey-Derived Persona Prompt Collection for Population-Aligned LLM Studies

Summary

LLM-based simulation of human views through persona prompting is increasingly common, but few persona collections are carefully curated and tied to real population data. The authors address this gap by releasing GGSS Personas, built from the ALLBUS (German General Social Survey) 2023 wave. Each of the survey's respondents becomes exactly one persona. Every persona combines a fixed block of core socio-demographics with a variable block of attributes, chosen by a global ranking of variable importance (TOP-k). The collection comes in two forms: structured JSON and LLM-written natural-language descriptions.

To test it, the authors asked several LLMs to reproduce how the population's answers are distributed across many survey topics. Models guided by these personas beat state-of-the-art classifiers, and the advantage is largest when little training data is available. The authors also examine how representativity and attribute choice affect alignment.

The resource matters because it is cheap to use, works across models and tasks, and is grounded in a probability sample. It also offers a reusable template for turning other national social surveys into persona collections.

Key points

  • Size and source: 5,246 personas, one per respondent of ALLBUS 2023. Fieldwork ran April–September 2023, and the data were released in January 2025. The full survey has 605 variables. The openly available ALLBUScompact, with 579 variables, served as the base.
  • Attribute selection: up to 380 ranked variables, with TOP-k ranging from 2 to 380. Missing answers mean the average number of filled attributes stays below k (e.g., about 242 at k=380).
  • Completeness: fully complete personas number 3,374 at TOP-2, 1,848 at TOP-4 and 821 at TOP-8, and none at higher k. All personas, including incomplete ones, are released so that users can choose between representativity and completeness.
  • Comparison with prior work: unlike PERSONA (1,586 synthetic personas from US census data, limited to 31 variables), GGSS Personas maps each persona to a real respondent. It also selects attributes automatically from the whole survey.
  • Access: available after registration at DOI 10.4232/1.14707. Stated limitations include:
    • each persona is a snapshot in time;
    • possible leakage across ALLBUS waves;
    • attribute ranking ignores multicollinearity;
    • LLM outputs are sensitive to prompt perturbations.

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

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.63317/2sod6uekicbg

@inproceedings{rupprecht2026german,
  title = {{German General Social Survey Personas: A Survey-Derived Persona Prompt Collection for Population-Aligned LLM Studies}},
  author = {Rupprecht, Jens and Froehling, Leon and Wagner, Claudia and Strohmaier, Markus},
  booktitle = {Proceedings of the Fifteenth Language Resources and Evaluation Conference},
  year = {2026},
  doi = {10.63317/2sod6uekicbg},
  url = {https://doi.org/10.63317/2sod6uekicbg}
}

References

52 references, 9 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Gati V. Aher, Rosa I. Arriaga, and Adam Tauman Kalai. 2023. Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies. In Proceedings of the 40th International Conference on Machine Learning, volume 202 of Proceedings of Machine Learning Research, pages 337–371. PMLR. ↗
  2. Jacy Reese Anthis, Ryan Liu, Sean M. Richardson, Austin C. Kozlowski, Bernard Koch, Erik Brynjolfsson, James Evans, and Michael S. Bernstein. 2025. Position: LLM Social Simulations Are a Promising Research Method. In ICML 2025 Position Paper Track, 42nd International Conference on Machine Learning. find
  3. Lisa P. Argyle, Ethan C. Busby, Nancy Fulda, Joshua R. Gubler, Christopher Rytting, and David Wingate. 2023. Out of One, Many: Using Language Models to Simulate Human Samples. Political Analysis, 31(3):337–351. ↗ our card
  4. Joshua Ashkinaze, Emily Fry, Narendra Edara, Eric Gilbert, and Ceren Budak. 2025. Plurals: A System for Guiding LLMs via Simulated Social Ensembles. In Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems, pages 1–21. ↗
  5. Tilman Beck, Hendrik Schuff, Anne Lauscher, and Iryna Gurevych. 2024. Sensitivity, Performance, Robustness: Deconstructing the Effect of Sociodemographic Prompting. In Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2589–2615. find
  6. Yong Cao, Haijiang Liu, Arnav Arora, Isabelle Augenstein, Paul Röttger, and Daniel Hershcovich. 2025. Specializing Large Language Models to Simulate Survey Response Distributions for Global Populations. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 3141–3154. ↗
  7. Louis Castricato, Nathan Lile, Rafael Rafailov, Jan-Philipp Fränken, and Chelsea Finn. 2025. PER-SONA: A Reproducible Testbed for Pluralistic Alignment. In Proceedings of the 31st International Conference on Computational Linguistics, pages 11348–11368. find
  8. Jiangjie Chen, Xintao Wang, Rui Xu, Siyu Yuan, Yikai Zhang, Wei Shi, Jian Xie, Shuang Li, Ruihan Yang, Tinghui Zhu, Aili Chen, Nianqi Li, Lida Chen, Caiyu Hu, Siye Wu, Scott Ren, Ziquan Fu, and Yanghua Xiao. 2024. From Persona to Personalization: A Survey on Role-Playing Language Agents. Transactions on Machine Learning Research. Survey Certification. ↗
  9. Runjin Chen, Andy Arditi, Henry Sleight, Owain Evans, and Jack Lindsey. 2025a. Persona Vectors: Monitoring and Controlling Character Traits in Language Models. arXiv preprint arXiv:2507.21509. ↗
  10. Sihan Chen, John P. Lalor, Yi Yang, and Ahmed Abbasi. 2025b. PersonaTwin: A Multi-Tier Prompt Conditioning Framework for Generating and Evaluating Personalized Digital Twins. In Proceedings of the Fourth Workshop on Generation, Evaluation and Metrics (GEM 2 ), pages 774–788. find
  11. Myra Cheng, Esin Durmus, and Dan Jurafsky. 2023a. Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language Models. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1504– 1532. find our card
  12. Myra Cheng, Tiziano Piccardi, and Diyi Yang. 2023b. CoMPosT: Characterizing and Evaluating Caricature in LLM Simulations. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 10853– 10875. find
  13. Pedro Henrique Luz de Araujo, Paul Röttger, Dirk Hovy, and Benjamin Roth. 2025. Principled Personas: Defining and Measuring the Intended Effects of Persona Prompting on Task Performance. arXiv preprint arXiv:2508.19764. ↗
  14. Wesley Hanwen Deng, Sunnie S. Y. Kim, Akshita Jha, Ken Holstein, Motahhare Eslami, Lauren Wilcox, and Leon A. Gatys. 2025. Personateam-ing: Exploring How Introducing Personas Can Improve Automated AI Red-Teaming. arXiv preprint arXiv:2509.03728. ↗
  15. Esin Durmus, Karina Nguyen, Thomas Liao, Nicholas Schiefer, Amanda Askell, Anton Bakhtin, Carol Chen, Zac Hatfield-Dodds, Danny Hernandez, Nicholas Joseph, et al. 2024. Towards Measuring the Representation of Subjective Global Opinions in Language Models. In First Conference on Language Modeling. ↗ our card
  16. Shangbin Feng, Chan Young Park, Yuhan Liu, and Yulia Tsvetkov. 2023. From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Models. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 11737– 11762. find our card
  17. Leon Fröhling, Gianluca Demartini, and Dennis Assenmacher. 2025. Personas With Attitudes: Controlling LLMs for Diverse Data Annotation. In Proceedings of the The 9th Workshop on Online Abuse and Harms (WOAH). ↗
  18. GESIS Leibniz-Institut für Sozialwissenschaften. 2025a. find
  19. German General Social Survey ALL-BUS 2023. (ZA8830; Version 1.2.0) [Data set]. GESIS, Cologne. https://doi.org/10.4232/1.14544. ↗
  20. GESIS Leibniz-Institut für Sozialwissenschaften. 2025b. find
  21. German General Social Survey ALLBUScompact 2023. (ZA8831; Version 1.3.0) [Data set]. GESIS, Cologne. https://doi.org/10.4232/1.14545. ↗
  22. Tao Ge, Xin Chan, Xiaoyang Wang, Dian Yu, Haitao Mi, and Dong Yu. 2024. Scaling Synthetic Data Creation With 1,000,000,000 Personas. arXiv preprint arXiv:2406.20094. ↗ our card
  23. Augusto Gonzalez-Bonorino, Monica Capra, and Emilio Pantoja. 2025. LLMs Model Non-WEIRD Populations: Experiments With Synthetic Cultural Agents. arXiv preprint arXiv:2501.06834. ↗
  24. Luke Hewitt, Ashwini Ashokkumar, Isaias Ghezae, and Robb Willer. 2024. Predicting Results of Social Science Experiments Using Large Language Models. Preprint. find
  25. Tiancheng Hu and Nigel Collier. 2024. Quantifying the Persona Effect in LLM Simulations. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 10289–10307. ↗
  26. Eunjeong Hwang, Bodhisattwa Majumder, and Niket Tandon. 2023. Aligning Language Models to User Opinions. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 5906–5919. find
  27. Junseok Kim, Nakyeong Yang, and Kyomin Jung. 2024. Persona Is a Double-Edged Sword: Mitigating the Negative Impact of Role-Playing Prompts in Zero-Shot Reasoning Tasks. arXiv preprint arXiv:2408.08631. ↗
  28. Junsol Kim and Byungkyu Lee. 2023. AI-Augmented Surveys: Leveraging Large Language Models and Surveys for Opinion Prediction. arXiv preprint arXiv:2305.09620. ↗
  29. Hannah Rose Kirk, Bertie Vidgen, Paul Röttger, and Scott A. Hale. 2024. The Benefits, Risks and Bounds of Personalizing the Alignment of Large Language Models to Individuals. Nature Machine Intelligence, 6(4):383–392. ↗
  30. William Kruskal and Frederick Mosteller. 1979. Representative Sampling, II: Scientific Literature, Excluding Statistics. International Statistical Review/Revue Internationale de Statistique, pages 111–127. ↗
  31. Woosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng, Lianmin Zheng, Cody Hao Yu, Joseph Gonzalez, Hao Zhang, and Ion Stoica. 2023. Efficient Memory Management for Large Language Model Serving With PagedAttention. In Proceedings of the 29th Symposium on Operating Systems Principles, pages 611–626. find
  32. Marlene Lutz, Indira Sen, Georg Ahnert, Elisa Rogers, and Markus Strohmaier. 2025. The Prompt Makes the Person(a): A Systematic Evaluation of Sociodemographic Persona Prompting for Large Language Models. arXiv preprint arXiv:2507.16076. ↗
  33. Bolei Ma, Berk Yoztyurk, Anna-Carolina Haensch, Xinpeng Wang, Markus Herklotz, Frauke Kreuter, Barbara Plank, and Matthias Aßenmacher. 2025. Algorithmic Fidelity of Large Language Models in Generating Synthetic German Public Opinions: A Case Study. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1785– 1809. ↗
  34. Fernando Miranda and Pedro Paulo Balbi. 2025. Simulating Public Opinion: Comparing Distributional and Individual-Level Predictions from LLMs and Random Forests. Entropy, 27(9):923. ↗
  35. Matthias Orlikowski, Jiaxin Pei, Paul Röttger, Philipp Cimiano, David Jurgens, and Dirk Hovy. 2025. Beyond Demographics: Fine-Tuning Large Language Models to Predict Individuals’ Subjective Text Perceptions. arXiv preprint arXiv:2502.20897. ↗
  36. Joon Sung Park, Carolyn Q. Zou, Aaron Shaw, Benjamin Mako Hill, Carrie Cai, Meredith Ringel Morris, Robb Willer, Percy Liang, and Michael S. Bernstein. 2024. Generative Agent Simulations of 1,000 People. arXiv preprint arXiv:2411.10109. ↗
  37. Tiany Peng, George Gui, Daniel J. Merlau, Grace Jiarui Fan, Malek Ben Sliman, Melanie Brucks, Eric J. Johnson, Vicki Morwitz, Abdullah Althenayyan, Silvia Bellezza, et al. 2025. A Mega-Study of Digital Twins Reveals Strengths, Weaknesses and Opportunities for Further Improvement. arXiv preprint arXiv:2509.19088. ↗
  38. Jens Rupprecht, Georg Ahnert, and Markus Strohmaier. 2025. Prompt perturbations reveal human-like biases in large language model survey responses. arXiv preprint arXiv:2507.07188. ↗
  39. Paulo Salem, Robert Sim, Christopher Olsen, Prerit Saxena, Rafael Barcelos, and Yi Ding. 2025. TinyTroupe: An LLM-Powered Multiagent Persona Simulation Toolkit. arXiv preprint arXiv:2507.09788. ↗
  40. Shibani Santurkar, Esin Durmus, Faisal Ladhak, Cinoo Lee, Percy Liang, and Tatsunori Hashimoto. 2023. Whose Opinions Do Language Models Reflect? In International Conference on Machine Learning, pages 29971–30004. PMLR. ↗ our card
  41. David O. Sears. 1986. College Sophomores in the Laboratory: Influences of a Narrow Data Base on Social Psychology’s View of Human Nature. Journal of Personality and Social Psychology, 51(3):515. ↗
  42. Indira Sen, Marlene Lutz, Elisa Rogers, David Garcia, and Markus Strohmaier. 2025. Missing the Margins: A Systematic Literature Review on the Demographic Representativeness of LLMs. In Findings of the Association for Computational Linguistics: ACL 2025, pages 24263–24289. Association for Computational Linguistics. ↗
  43. Freda Shi, Xinyun Chen, Kanishka Misra, Nathan Scales, David Dohan, Ed H. Chi, Nathanael Schärli, and Denny Zhou. 2023. Large Language Models Can Be Easily Distracted by Irrelevant Context. In International Conference on Machine Learning, pages 31210–31227. PMLR. ↗ our card
  44. Taylor Sorensen, Jared Moore, Jillian Fisher, Mitchell Gordon, Niloofar Mireshghallah, Christopher Michael Rytting, Andre Ye, Liwei Jiang, Ximing Lu, Nouha Dziri, et al. 2024. Position: A Roadmap to Pluralistic Alignment. In Proceedings of the 41st International Conference on Machine Learning, pages 46280–46302. find our card
  45. Joseph Suh, Erfan Jahanparast, Suhong Moon, Minwoo Kang, and Serina Chang. 2025. Language Model Fine-Tuning on Scaled Survey Data for Predicting Distributions of Public Opinions. In 80th Annual AAPOR Conference. AAPOR. find
  46. Chenkai Sun, Ke Yang, Revanth Gangi Reddy, Yi Fung, Hou Pong Chan, Kevin Small, ChengXiang Zhai, and Heng Ji. 2025. Persona-DB: Efficient Large Language Model Personalization for Response Prediction With Collaborative Data Refinement. In Proceedings of the 31st International Conference on Computational Linguistics, pages 281–296. ↗
  47. Lindia Tjuatja, Valerie Chen, Tongshuang Wu, Ameet Talwalkwar, and Graham Neubig. 2024. Do LLMs Exhibit Human-like Response Biases? A Case Study in Survey Design. Transactions of the Association for Computational Linguistics, 12:1011–1026. find
  48. Olivier Toubia, George Z. Gui, Tianyi Peng, Daniel J. Merlau, Ang Li, and Haozhe Chen. 2025. Database Report: Twin-2K-500: A Data Set for Building Digital Twins of Over 2,000 People Based on Their Answers to Over 500 Questions. Marketing Science. ↗
  49. Yu-Min Tseng, Yu-Chao Huang, Teng-Yun Hsiao, Wei-Lin Chen, Chao-Wei Huang, Yu Meng, and Yun-Nung Chen. 2024. Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalization. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 16612– 16631. find
  50. Leah von der Heyde, Anna-Carolina Haensch, and Alexander Wenz. 2025. Vox Populi, Vox AI? Using Large Language Models to Estimate German Vote Choice. Social Science Computer Review. find
  51. Angelina Wang, Jamie Morgenstern, and John P. Dickerson. 2025. Large Language Models That Replace Human Participants Can Harmfully Misportray and Flatten Identity Groups. Nature Machine Intelligence, pages 1–12. ↗
  52. Zhehao Zhang, Ryan A. Rossi, Branislav Kveton, Yijia Shao, Diyi Yang, Hamed Zamani, Franck Dernoncourt, Joe Barrow, Tong Yu, Sungchul Kim, Ruiyi Zhang, Jiuxiang Gu, Tyler Derr, Hongjie Chen, Junda Wu, Xiang Chen, Zichao Wang, Subrata Mitra, Nedim Lipka, Nesreen K. Ahmed, and Yu Wang. 2025. Personalization of Large Language Models: A Survey. Transactions on Machine Learning Research. Survey Certification. ↗ our card

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/rupprecht-2026-german-general-social-survey-personas/