Synthetic Replacements for Human Survey Data? The Perils of Large Language Models

Cited by (209)

Items 101–200 of 209

1. Be.FM: Open Foundation Models for Human Behavior
   Yutong Xie, Ziqing Li, Xiyuan Wang, Yijun Pan, Qijia Liu, Xingzhi Cui, Kuang-Yu Lo, Ruoyi Gao, Xingjian Zhang, Jincheng Huang et al. · 2025 · SSRN Electronic Journal
2. Assessing Bias in LLM-Generated Synthetic Datasets: The Case of German Voter Behavior
   Leah von der Heyde, Anna‐Carolina Haensch, Alexander Wenz · 2023
3. Once Upon a Time: Introducing the Historical Values Survey
   Mahdi Khesali, Stefan Voigt, Nadia von Jacobi · 2025 · SSRN Electronic Journal
4. Ranking Business Trade Preferences using GPT
   Rodrigo Fagundes Cézar · 2025 · SSRN Electronic Journal
5. Large Language Models(LLMs) in Political Science Research: Analysis of Topical Trends and Usage Patterns
   Inbok Rhee · 2025 · Korean Journal of International Relations
6. Exploring the Learning Styles of "Semi-Humans": A Comparative Study of Nine Large Language Models
   Yangxiaoyu Yang, Tao Wang, Dayong Shen, Feng Yao, Shan Huang · 2025 · International Conference on Computer Technology Applications (ICCTA)
7. Empirical Examination of Large Language Models in Regional Psychological Structures Simulation: Personality and Well-being
   Xing Zhou, Jiahong Zheng · 2025 · Research Square
8. Public polling
   Arnold Lau, Scott Keeter · 2025 · Elsevier eBooks
9. How LLMs Handle Cultural Bias: Reactions to Asian Minority Historical Narratives
   Shirin Shujaa, Ginel Dorleon, Arthur Tang · 2025 · Lecture notes in computer science
10. Moral reasoning and synthetic judgment in large language models
    Thierry Poibeau · 2025 · Ubiquity Press eBooks
11. LLM Survey Framework: Coverage, Consistency, Identification
    Jing Cynthia Wu, Jin Xi, Shihan Xie · 2025 · SSRN Electronic Journal
12. AI Simulations of Audience Attitudes and Policy Preferences: “Silicon Sampling” Guidance for Communications Practitioners
    John Wihbey, Samantha D'Alonzo · 2025 · SSRN Electronic Journal
13. Psychometric Comparability of LLM-Based Digital Twins
    Yufei Zhang, Zhihao Ma · 2026 · SSRN Electronic Journal
14. Conducting Innovative Thought Experiments and Simulations With Large Language Models
    İbrahim Niftiyev · 2026 · IGI Global eBooks
15. The Price of Digital Compassion: Exposing and Managing Latent Risks in AI Survey Augmentation
    Yujie Chi, Dazhou Lei · 2026 · SSRN Electronic Journal
16. Living Labs as Innovation Catalysts in the Silver Economy
    Göran Roos · 2026 · IGI Global eBooks
17. How Many Human Survey Respondents is a Large Language Model Worth? An Uncertainty Quantification Perspective
    Chengpiao Huang, Yuhang Wu, Kaizheng Wang · 2026 · SSRN Electronic Journal
18. Surveying with AI: Simulating Human Responses Using Personalized LLM Agents and Social Media Data
    Shuxi Liang, Haolin Ren, Tianze Zhang, Xiaofan Liu, Zhimeng Yin, Daning Hu · 2025 · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics
19. Generation of Synthetic Data in Health Surveys Using Large Language Models
    David Villarreal‐Zegarra, Luciana Bellido-Boza · 2026 · medRxiv
20. How Marketers Can Utilize Generative AI in Qualitative Research
    Omar H. Fares · 2026 · Springer eBooks
21. Computational Basis of Large Language Models’ Decision Making in Social Simulation
    Ji Ma · 2026 · Sociological Methodology
22. Beyond human proxies: The roles and usefulness of large language models in user research for mobility service development
    Eetu Wallius, Esko Lehtonen · 2026 · Transportation Research Interdisciplinary Perspectives
23. Approximating Consumer Preferences Before Market Entry: Large Language Models as Decision-Support Tools in Early-Stage New Product Development
    Haejun Jung, Jaeyun Lee, Sungwon Lee, Doohee Chung · 2026 · SSRN Electronic Journal
24. Polypersona: Persona-Grounded LLM for Synthetic Survey Responses
    Tejaswani Dash, Dinesh Karri, Anudeep Vurity, Gautam Varma Datla, Tazeem Ahmad, Saima Rafi, Rohith Tangudu · 2025 · IEEE International Conference on Big Data (BigData)
25. LLMs as complementary tools for innovation surveys research: pattern replication and contextual relevance
    Jae Hyung Park, Jae-Suk Yang · 2026 · Scientometrics
26. A Cross-Cultural Comparison of LLM-Based Public Opinion Simulation: Evaluating Chinese and U.S. Models on Diverse Societies
    Weihong Qi, Fan Huang, Jisun An, Haewoon Kwak · 2025 · IEEE ... International Conference on Data Mining workshops
27. Stochastic Parrots or Singing in Harmony? Testing Five Leading LLMs for their Ability to Replicate a Human Survey with Synthetic Data
    Jason Miklian, Kristian Hoelscher, John E. Katsos · 2026 · SSRN Electronic Journal
28. Experimental comparison of a chatbot-like questionnaire design with a traditional web questionnaire design
    Ceyda Çavusoglu Deveci, Marek Fuchs, Anke Metzler · 2026 · Bulletin of Sociological Methodology/Bulletin de Méthodologie Sociologique
29. Survey Research With AI
    2026 · Advances in computational intelligence and robotics book series
30. Generative AI for climate governance and acceptability-constrained policy design
    Ajaykumar Manivannan, Viktoria Spaiser, Tristan J. B. Cann, James Evans, Jordan Everall, Max Falkenberg, David García, Weisi Guo, Rico Herzog, Ilona M. Otto et al. · 2026 · npj Climate Action
31. Simulating Lay Health-Seeking Behavior with LLM Personas and Illness Vignettes: Reproducibility, Prompt Sensitivity, and Slice Dependence
    Yuusuke Harada · 2026 · Qeios
32. Small is Beautiful : addressing resource scarcity, language variation, and transfer challenges for automatic detection of Harmful language
    Arij Riabi · 2025 · theses.fr (ABES)
33. Establishing Reliability and Validity Evidence for Artificial Intelligence-Based Scores Application to the Organizational Sciences
    Andrew B. Speer, Frederick Louis Oswald, Dan J. Putka · 2026
34. LLMs and Data Management for International Relations Scholars: Moving Beyond EuGene-Style Software
    Paul Poast · 2026 · SSRN Electronic Journal
35. Stochastic Parrots or Singing in Harmony? Testing Five Leading LLMs for their Ability to Replicate a Human Survey with Synthetic Data
    Jason Miklian, Kristian Hoelscher, John Katsos · 2026 · SSRN Electronic Journal
36. Can LLMs Mimic Household Surveys?: From Representative Agents to Population Distributions
    Ami Dalloul, Moritz Pfeifer · 2026 · SSRN Electronic Journal
37. Evolving and Detecting Multi-Turn Deception using Geometric Signatures
    Surender Suresh Kumar, Mary L. Cummings · 2026 · SSRN Electronic Journal
38. Giving texture to theory: A computational thought experiment on opportunity capital with LLM agents
    Dimo P. Dimov · 2026 · Journal of Business Venturing Insights
39. Simulating Lay Health-Seeking Behavior with LLM Personas and Illness Vignettes: Reproducibility, Prompt Sensitivity, and Slice Dependence
    Yuusuke Harada · 2026 · Qeios
40. Assessment of LLMs for Generating Synthetic Health-Related Quality-of-Life Survey Responses Among U.S. Adults
    Seungkook Baek, Sunghyun Lee, Hyungjin Kim, Sungchul Park · 2026 · American Journal of Preventive Medicine
41. Exploring migration research with large language model: methods and insights
    S. Iacus, Hao-Dong Qi, Jiyoung Han · 2026 · Royal Society Open Science
42. Value Contamination in Policy Simulation: Measuring How LLM Policy-Value Orientations Shape Predicted Administrative Burden Effects
    Yichao Jin · 2026 · SSRN Electronic Journal
43. Thinking Outside the Black Box: Seven Guidelines for GenAI Use in the Ecological Sciences
    Nina C. Ferrari, Emily E. Conklin, Amelia Fitch, Dustin G. Gannon, Rossana Macedo, Aidan Place, Hannah R. Sachs, Eugene Seo, Matthew J. Weldy, Matthew G. Betts · 2026 · Ecology and Evolution
44. Synthetic Personas for Scaling Privacy Research in Education
    Kimaya Padmashali, Pedrycz Wiktor, Oleksandra Poquet · 2026 · ACM Conference on Learning @ Scale (L@S)
45. The Collapse of Heterogeneity in Silicon Philosophers
    Yuanming Shi, Andreas Alexander Haupt · 2026 · ACM Conference on Fairness, Accountability, and Transparency (FAccT)
46. Informing AI Policy Assessment using Large-Scale Simulation of Interventions
    Julia Barnett, Kimon Kieslich, Natali Helberger, Nicholas A. Diakopoulos · 2026 · ACM Conference on Fairness, Accountability, and Transparency (FAccT)
47. The Context Dependency of Demographic Bias in LLM Annotation
    Megan A. Brown, Shubham Atreja, Libby Hemphill, Patrick Y. Wu · 2026 · ACM Conference on Fairness, Accountability, and Transparency (FAccT)
48. Evaluation Criteria for Synthetic Respondents in Qualitative Research: Limits of Applicability
    Kirill Zhulikov · 2026 · Inter
49. Testing of AI-generated Autobiographies for Studying the Life Course
    Anna Vladimirovna Andreenkova · 2026 · Inter
50. Synthetic survey data in renewable energy acceptance research: A validity audit using PLS-SEM
    Tanvi Bhatia, Gnana K. Bharathy, Mukesh Prasad · 2026 · Energy Sustainable Development/Energy for sustainable development
51. Humanos frente a tres modelos del lenguaje en educación patrimonial: un análisis comparativo mediante la escala Q-HeriLearn
    Víctor E. Gil-Biraud, Pablo de Castro, Olaia Fontal Merillas · 2026 · Ense�anza de las Ciencias Sociales
52. Silicon Sampling via Cross-Survey Transfer
    Chan-Tung Ku, Chan Hsu, Pei-Cing Huang, Frank Cheng-Shan Liu, I-Ling Cheng, Yihuang Kang · 2026 · IEEE International Conference on Information Reuse and Integration (IRI)
53. Judicious use of LLMs could speed up progress in the social sciences
    James N. Druckman · 2026 · Nature
54. Forecasting the Future Through a Partisan Lens: Electoral Outcomes and Household Expectations
    Sergii Drobot, Nayeon Kang · 2026 · SSRN Electronic Journal
55. Minimal Viable Cognitive Agent (MVCA): Building a glass-box LLM cognitive architecture for testing process theories in Agent psychonomicus
    Jack Chen, WeiHeng Xiao · 2026 · SSRN Electronic Journal
56. Chorus: An Agentic Framework for Generating Realistic Deliberation Data
    Athanasios Koursaris, George Domalis, Alexandra Apostolopoulou, Konstantinos Kanaris, Dimitris Tsakalidis, Ioannis E. Livieris · 2026 · Communications in computer and information science
57. Synthetic data and digital twins: The hype, the facts, the promise
    Olivier Toubia · 2026 · Current Opinion in Psychology
58. AI and citizen participation: a political economy lens
    Nathan Davies, Flynn Devine · 2026 · Data & Policy
59. Designing Data Centers for Demand Response Through a Construction-Phase Readiness Index
    Arezou Shafaghat, Da Hu, Ali Keyvanfar · 2026 · Buildings
60. Generation of Synthetic Samples by Large Language Models in the Context of Cross-Country Surveys
    Elizaveta Kuznechenkova, Maria Nesterskaya, Vera Semenova · 2026 · IEEE International Conference on AI and Data Analytics (ICAD)
61. The End of Theory in Social Science? AI and Sleepwalking into Epistemic Surrender
    A N Smith, Clare Humphries · 2026 · SSRN Electronic Journal
62. From institutional trust to AI adoption: a trust transfer and risk perception model of AI-enabled public service acceptance in China's digital government context
    Huihui Wang, Shixin Zhu · 2026 · Frontiers in Psychology
63. Artificial Consensus: AI and Survey Measurement
    Thomas Cauthorn · 2026 · SSRN Electronic Journal
64. Beyond the Conventional Pipeline: Large Language Models for Social Science Measurement
    Lê Thái Bảo · 2026 · Chinese Political Science Review
65. Enhancing Counselor Education With Artificial Intelligence Chatbots: Attitudes Toward Artificial Intelligence and Counseling Skill Self‐Efficacy
    Eunae Han, Pei‐Ling Hsu, Jihoon Shin · 2026 · Journal of Counseling & Development
66. Can silicon citizens replace human respondents? Validating large language models against human choice and valuation data
    E.H. Cho, Juyong Lee · 2026 · SSRN Electronic Journal
67. Distributional Alignment for Social Simulation with LLMs: A Mixture Modeling Approach
    Yutong Xie, Ruoyi Gao, Qiao-Zhu Mei · 2026 · Knowledge Discovery and Data Mining
68. Drivers of Generative AI Acceptance in Agriculture: An AHP Study with Synthetic Experts *
    Murat Tahir Çaldağ · 2026 · International Conference on Control, Decision and Information Technologies (CoDIT)
69. Not for people like me: How frontier AI models redirect skeptical rural school staff
    Zachary Rossmiller · 2026 · Computers and Education Artificial Intelligence
70. Navigating AI disruption: Systems theory framework for the European Social Survey
    Brina Malnar · 2026 · Current Sociology
71. Generative AI for Surveys on Payment Apps: AI Views on Privacy and Technology
    Koji Takahashi, Joon Park · 2026 · SSRN Electronic Journal
72. Auditing LLM-based Synthetic Expert Panels for AHP: A Preregistered Benchmark and Prospective Order-randomization Test
    Howard Kim, Keuntae Cho · 2026 · SSRN Electronic Journal
73. Emergent Health Preferences in Large Language Models: A Time-Trade-Off Analysis Using EQ-5D-3L
    Patrik P. Süli, György Eigner, Zsombor Zrubka · 2026 · IEEE International Conference on Intelligent Engineering Systems (INES)
74. Calibrated synthetic consumer panels for governed strategic market testing
    Oyindamola L. Lawal, Olamide F Orisakahunsi, Ogechi M. Ikeakaonwu, Elizabeth I. Igbodor, Adeyemi A. Adefisan-Williams, Ngozi B. Umoru, Saheed A. Adeniyi, Adeyemi A. Adefisan-Williams, Rukayat A. Olawaled and Elizabeth I. Igbodor, Priscilla Kuyet Ishaku · 2026 · Strategic Business Research
75. LLMs Do Not Emulate Populations
    B.S Green, Greg Leo · 2026 · SSRN Electronic Journal
76. Between purpose and strategy: How corporations amplify CEO activism on social media
    Jia-Cheng Huang, Yi-Hui Ji · 2026 · Public Relations Review
77. Global Trends in Research Ethics in the Context of Artificial Intelligence
    Hakile Resulbegoviq · 2026 · Advances in computational intelligence and robotics book series
78. RAD-MRM: A Multi-Source Data-Integrated Methodology for Mining User Requirements in Industrial-Heritage Tourism
    Zhi Qiao, Shuai Yuan, Yanmin Xue, Wei Zhou, Shuang Wang, Kai Qi · 2026 · International Journal of Human-Computer Interaction
79. Don’t Look up: Evaluating the Tradeoff Between Performance and Sustainability of Text Classification Using Open LLMs
    Sean-Kelly Palicki, Isaac Bravo, Clint Claessen · 2026 · Social Science Computer Review
80. Can large language models replace human surveys in geospatial studies? A case of vague cognitive regions
    Yue Lin, Ningchuan Xiao · 2026 · Spatial Cognition and Computation
81. Epistemic Displacement Theory: Understanding the Transformation of Consumer Knowledge in the Age of Synthetic Respondents
    Hyungjin Lukas Kim · 2026 · Journal of Macromarketing
82. LLMRpanel: Benchmarked Silicon Samples for Survey and Experiment Design
    Ali Sanaei · 2026
83. Synthetic data in research: expert perceptions and a protocol for responsible GenAI use
    Tarik Doğru, Makarand Amrish Mody, Anil Bilgihan, A. George Assaf · 2026 · International Journal of Contemporary Hospitality Management
84. Mathematical Sociology: Models, Structures, and Open Problems
    Dimitri Volchenkov · 2026 · Mathematics
85. Moral Inflation in Synthetic Investors: When LLM Personas Replace Heterogeneity with Normative Archetypes
    Seungho Jeon, H. Steve Leslie, Hrishikesh Desai · 2026 · SSRN Electronic Journal
86. Algorithmic systems, human agency and the future of platform research
    Homa Hosseinmardi, Upasana Dutta, David M. Rothschild, Duncan J. Watts · 2026 · Nature Computational Science
87. Epistemic Capabilities of Artificial Intelligence for Public Administration and Policy Research: A Framework for Scholarship in the Age of Intelligent Machines
    Yanto Chandra, Jianxiang Tan · 2026 · Policy Studies Journal
88. User engagement behaviours with identity-disclosed social bots on social media: the role of perceived human–machine differences
    Hao Xu, Shaobo Liang, Jing Dong, Qingxuan Cheng · 2026 · Aslib Journal of Information Management
89. Which AI? A Comparative Evaluation of Generative AI and Neuro‐Symbolic AI for Silicon Sampling
    Kamila Zahradníčková, Jan Polišenský, Martin Lukeš, Radek Hranický, Petr Pouč · 2026 · Psychology and Marketing
90. Get a learner’s permit before you speed on the highway: farewell and a call for a priori model evaluation metrics and guardrails for computational communication research
    Lijiang Shen · 2026 · Communication Methods and Measures
91. Psychologische Forschung zu Zeiten generativer KI: Eine methodische Positionierung
    Jona Carmon, Martin Rolfs, Melanie Caroline Steffens, Andrea Kiesel, Thorsten Meiser, Gudrun Schwarzer, Simone Kühn · 2026 · Psychologische Rundschau
92. KI in der Umfrageforschung
    Marek Fuchs · 2026 · Springer eBooks
93. Simulated responses from large language models are weak proxies for human economic preferences across 74 countries
    Fadong Chen, Qijun Wang, Lei Wang, Sudeep Bhatia · 2026 · Nature Human Behaviour
94. Using Large Language Models to Construct Virtual Top Managers
    Antonio Garzón‐Vico, Krithika Komalapati, Arsalan Shahid, Jan Rosier · 2026 · SSRN Electronic Journal
95. When Synthetic Consumers Become Consumer Evidence: Evidence-Role Drift in AI-Mediated Market Research
    Lenin Heartly · 2026 · Octopus
96. Just a Simulation? A Review of Large Language Models as Subjects in Experimental Economics
    Ayato Kitadai, Nariaki Nishino · 2026 · SSRN Electronic Journal
97. What Is Left for Us? Second Scholarship Against the Degradation of Research by AI
    Claudio Novelli, Luciano Floridi · 2026 · European Law Journal
98. KETRIN: Elicitação Adaptativa de Conhecimento para Diagnóstico de Maturidade em Proteção de Dados
    Ketrin Diovana Alves Rodrigues Vargas, Tuigg R. Barcelos, Camilla Borchhardt Quincozes, Silvio E. Quincozes, Paulo Silas Severo de Souza · 2026 · Simpósio Brasileiro de Cibersegurança (SBSeg)
99. On the Impact of Item Order and Questionnaire Popularity for Language Model Construct Validity and Cross-Human Alignment
    Simon Münker, Simon Werner, Achim Rettinger · 2026 · Lecture notes in computer science
100. Estimating Decision Rules from Large Language Model Agents: An Application to Bank Balance-Sheet Management
     Zlatin Sarastov · 2026 · Research Square