mlsanityData to 14 Oct 2026

Random Silicon Sampling: Simulating Human Sub-Population Opinion Using a Large Language Model Based on Group-Level Demographic Information

arXiv 2402.18144 ↗First posted 28 Feb 2024cs.AI cs.CYcited by 49

Not on the map. Why?

Abstract (arXiv)

Large language models exhibit societal biases associated with demographic information, including race, gender, and others. Endowing such language models with personalities based on demographic data can enable generating opinions that align with those of humans. Building on this idea, we propose "random silicon sampling," a method to emulate the opinions of the human population sub-group. Our study analyzed 1) a language model that generates the survey responses that correspond with a human group based solely on its demographic distribution and 2) the applicability of our methodology across various demographic subgroups and thematic questions. Through random silicon sampling and using only group-level demographic information, we discovered that language models can generate response distributions that are remarkably similar to the actual U.S. public opinion polls. Moreover, we found that the replicability of language models varies depending on the demographic group and topic of the question, and this can be attributed to inherent societal biases in the models. Our findings demonstrate the feasibility of mirroring a group's opinion using only demographic distribution and elucidate the effect of social biases in language models on such simulations.

Key facts. Cited by 49 papers in the map (data through 14 Oct 2026). Builds on 28 of its 74 references that are in the map. First posted on arXiv 28 Feb 2024.

Builds on

28 of 74 references.

References · 28

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2022Discovering Language Model Behaviors with Model-Written Evaluationscited by 836
  3. 2023Whose Opinions Do Language Models Reflect?cited by 773
  4. 2022Out of One, Many: Using Language Models to Simulate Human Samplescited by 752
  5. 2023AGIEval: A Human-Centric Benchmark for Evaluating Foundation Modelscited by 716
  6. 2022Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studiescited by 515
  7. 2023Towards Measuring the Representation of Subjective Global Opinions in Language Modelscited by 437
  8. 2022Using cognitive psychology to understand GPT-3cited by 398
  9. 2023Toxicity in ChatGPT: Analyzing Persona-assigned Language Modelscited by 360
  10. 2023From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Modelscited by 260
  11. 2023Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language Modelscited by 207
  12. 2023Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMscited by 199
16 more
  1. 2023The political ideology of conversational AI: Converging evidence on ChatGPT's pro-environmental, left-libertarian orientationcited by 189
  2. 2021Large Pre-trained Language Models Contain Human-like Biases of What is Right and Wrong to Docited by 178
  3. 2023In-Context Impersonation Reveals Large Language Models' Strengths and Biasescited by 155
  4. 2023Aligning Language Models to User Opinionscited by 99
  5. 2023CoMPosT: Characterizing and Evaluating Caricature in LLM Simulationscited by 97
  6. 2023NLPositionality: Characterizing Design Biases of Datasets and Modelscited by 94
  7. 2022Moral Mimicry: Large Language Models Produce Moral Rationalizations Tailored to Political Identitycited by 74
  8. 2023Simulating Social Media Using Large Language Models to Evaluate Alternative News Feed Algorithmscited by 65
  9. 2022Identifying and Manipulating the Personality Traits of Language Modelscited by 40
  10. 2022CommunityLM: Probing Partisan Worldviews from Language Modelscited by 36
  11. 2023Large Language Models Can Be Used to Estimate the Latent Positions of Politicianscited by 33
  12. 2023Language Models Trained on Media Diets Can Predict Public Opinioncited by 30
  13. 2023Susceptibility to Influence of Large Language Modelscited by 17
  14. 2023Large Language Models as Subpopulation Representative Models: A Reviewcited by 16
  15. 2023Demonstrations of the Potential of AI-based Political Issue Pollingcited by 14
  16. 2023Can Large Language Models Capture Public Opinion about Global Warming? An Empirical Assessment of Algorithmic Fidelity and Biascited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 12; 2025: 15; 2026: 22.

49 papers.

Sort:

By area:

  1. 2025AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Societycited by 186
  2. 2024From Individual to Society: A Survey on Social Simulation Driven by Large Language Model-based Agentscited by 82
  3. 2024Large Language Models Assume People are More Rational than We Really arecited by 54
  4. 2025Specializing Large Language Models to Simulate Survey Response Distributions for Global Populationscited by 53
  5. 2024Beyond Demographics: Aligning Role-playing LLM-based Agents Using Human Belief Networkscited by 39
  6. 2024Evaluating Cultural Adaptability of a Large Language Model via Simulation of Synthetic Personascited by 37
  7. 2024The Potential and Challenges of Evaluating Attitudes, Opinions, and Values in Large Language Modelscited by 19
  8. 2025Valid Survey Simulations with Limited Human Data: The Roles of Prompting, Fine-Tuning, and Rectificationcited by 18
  9. 2025The threat of analytic flexibility in using large language models to simulate human datacited by 15
  10. 2024Algorithmic Fidelity of Large Language Models in Generating Synthetic German Public Opinions: A Case Studycited by 14
  11. 2025Beyond Static Responses: Multi-Agent LLM Systems as a New Paradigm for Social Science Researchcited by 10
  12. 2025Large Language Models as Virtual Survey Respondents: Evaluating Sociodemographic Response Generationcited by 7
37 more
  1. 2026MatrAIx: Simulating the World with 8.3 Billion Persona Agentscited by 7
  2. 2024Extracting Affect Aggregates from Longitudinal Social Media Data with Temporal Adapters for Large Language Modelscited by 4
  3. 2025ValueSim: Generating Backstories to Model Individual Value Systemscited by 4
  4. 2026Restoring Heterogeneity in LLM-based Social Simulation: An Audience Segmentation Approachcited by 4
  5. 2024Kiss up, Kick down: Exploring Behavioral Changes in Multi-modal Large Language Models with Assigned Visual Personascited by 3
  6. 2024LLM Generated Distribution-Based Prediction of US Electoral Results, Part Icited by 3
  7. 2026Beyond the Mean: Three-Axis Fidelity for Aligning LLM-Based Survey Simulators from Small Pilot Datacited by 3
  8. 2024The creative psychometric item generator: a framework for item generation and validation using large language modelscited by 2
  9. 2025Improving the Distributional Alignment of LLMs using Supervisioncited by 2
  10. 2025Exploring Large Language Model Agents for Piloting Social Experimentscited by 2
  11. 2024Intelligent Computing Social Modeling and Methodological Innovations in Political Science in the Era of Large Language Modelscited by 1
  12. 2025Can Large Language Models Predict Associations Among Human Attitudes?cited by 1
  13. 2025Reward Model Perspectives: Whose Opinions Do Reward Models Reward?cited by 1
  14. 2025Prompt Optimization Across Multiple Agents for Representing Diverse Human Populationscited by 1
  15. 2025Mitigating Social Desirability Bias in Random Silicon Samplingcited by 1
  16. 2026RADIUS: Ranking, Distribution, and Significance - A Comprehensive Alignment Suite for Survey Simulationcited by 1
  17. 2026Characterizing the ability of LLMs to recapitulate Americans' distributional responses to public opinion polling questions across political issuescited by 1
  18. 2026Improving Cross-Cultural Survey Simulation with Calibrated Value Personascited by 1
  19. 2026The conditional superiority of fast silicon samplingcited by 1
  20. 2026Aplaud: Adaptive Personalized Low-Rank Decomposition for User-Specific LLMcited by 1
  21. 2026When Can LLM Digital Twins Reduce Human Measurement? From Behavioral Fidelity to Statistical Substitutabilitycited by 1
  22. 2026The Limits of Simulated Societies: How Post-Training and Survey Fine-Tuning Erase Cross-Cultural Variancecited by 1
  23. 2026Consequential Behaviour and Representational Fairness in the Validation of Synthetic Researchcited by 1
  24. 2024Are Social Sentiments Inherent in LLMs? An Empirical Study on Extraction of Inter-demographic Sentimentscited by 0
  25. 2025Leveraging Interview-Informed LLMs to Model Survey Responses: Comparative Insights from AI-Generated and Human Datacited by 0
  26. 2025A hierarchy tree data structure for behavior-based user segment representationcited by 0
  27. 2026Visual Affect Analysis: Predicting Emotions of Image Viewers with Vision-Language Modelscited by 0
  28. 2026Beyond Static Snapshots: Dynamic Modeling and Forecasting of Group-Level Value Evolution with Large Language Modelscited by 0
  29. 2026Reasoning Boosts Opinion Alignment in LLMscited by 0
  30. 2026Can Large Language Models Revolutionize Survey Research? Experiments with Disaster Preparedness Responsescited by 0
  31. 2026Co-design of LLM-based preference agents: participation may drive overtrustcited by 0
  32. 2026Emulate or Estimate? The Divergent Strengths of Base and Post-Trained Language Models for Opinion Simulationcited by 0
  33. 2026Analyzing and Correcting Benevolence Bias in Large Language Modelscited by 0
  34. 2026Belief Cascades Drive Persuasion in LLM Agent Networkscited by 0
  35. 2026Cultural Misalignment in Large Language Models: Detection, Measurement, and Mitigation Through Targeted Fine-Tuningcited by 0
  36. 2026From Process Loss to Assembly Bonus: Human-Grounded Diagnosis of Multi-Agent LLM Collaborationcited by 0
  37. 2026Data-Driven Personas for Survey Simulation: Insights into Simulation Alignment Across Data-Access Regimescited by 0