mlsanityData to 14 Oct 2026

A Large-Scale Simulation on Large Language Models for Decision-Making in Political Science

arXiv 2412.15291 ↗First posted 19 Dec 2024cs.CL cs.SIcited by 10

Not on the map. Why?

Abstract (arXiv)

While LLMs have demonstrated remarkable capabilities in text generation and reasoning, their ability to simulate human decision-making -- particularly in political contexts -- remains an open question. However, modeling voter behavior presents unique challenges due to limited voter-level data, evolving political landscapes, and the complexity of human reasoning. In this study, we develop a theory-driven, multi-step reasoning framework that integrates demographic, temporal and ideological factors to simulate voter decision-making at scale. Using synthetic personas calibrated to real-world voter data, we conduct large-scale simulations of recent U.S. presidential elections. Our method significantly improves simulation accuracy while mitigating model biases. We examine its robustness by comparing performance across different LLMs. We further investigate the challenges and constraints that arise from LLM-based political simulations. Our work provides both a scalable framework for modeling political decision-making behavior and insights into the promise and limitations of using LLMs in political science research.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 27 of its 59 references that are in the map. First posted on arXiv 19 Dec 2024.

Builds on

27 of 59 references.

References · 27

  1. 2021On the Opportunities and Risks of Foundation Modelscited by 4,033
  2. 2022Out of One, Many: Using Language Models to Simulate Human Samplescited by 752
  3. 2022Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studiescited by 515
  4. 2021Deep Neural Networks and Tabular Data: A Surveycited by 491
  5. 2021LexGLUE: A Benchmark Dataset for Legal Language Understanding in Englishcited by 310
  6. 2023From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Modelscited by 260
  7. 2024LLM Agents Grounded in Self-Reports Enable General-Purpose Simulation of Individualscited by 249
  8. 2023Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology Viewcited by 222
  9. 2022A Review on Language Models as Knowledge Basescited by 157
  10. 2023Simulating Opinion Dynamics with Networks of LLM-based Agentscited by 154
  11. 2020COPOD: Copula-Based Outlier Detectioncited by 146
  12. 2024Systematic Biases in LLM Simulations of Debatescited by 99
15 more
  1. 2019Evaluating Commonsense in Pre-trained Language Modelscited by 95
  2. 2024Generalization v.s. Memorization: Tracing Language Models' Capabilities Back to Pretraining Datacited by 85
  3. 2024Can Large Language Model Agents Simulate Human Trust Behavior?cited by 64
  4. 2024Is this the real life? Is this just fantasy? The Misleading Success of Simulating Social Interactions With LLMscited by 59
  5. 2024LLM economicus? Mapping the Behavioral Biases of LLMs via Utility Theorycited by 47
  6. 2024DrugAgent: Automating AI-aided Drug Discovery Programming through LLM Multi-Agent Collaborationcited by 44
  7. 2021Theme Transformer: Symbolic Music Generation with Theme-Conditioned Transformercited by 40
  8. 2024ElectionSim: Massive Population Election Simulation Powered by Large Language Model Driven Agentscited by 35
  9. 2023Large Language Models Can Be Used to Estimate the Latent Positions of Politicianscited by 33
  10. 2024LLMs generate structurally realistic social networks but overestimate political homophilycited by 33
  11. 2024Political-LLM: Large Language Models in Political Sciencecited by 27
  12. 2023Synthetic Data Applications in Financecited by 22
  13. 2020SYNC: A Copula based Framework for Generating Synthetic Data from Aggregated Sourcescited by 17
  14. 2023AdaRefiner: Refining Decisions of Language Models with Adaptive Feedbackcited by 10
  15. 2024Simulating The U.S. Senate: An LLM-Driven Agent Approach to Modeling Legislative Behavior and Bipartisanshipcited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 5.

10 papers.

  1. 2025StealthRank: LLM Ranking Manipulation via Stealthy Prompt Optimizationcited by 12
  2. 2025SocialMaze: A Benchmark for Evaluating and Enhancing Social Reasoning in Large Language Models in Complex Social Environmentscited by 11
  3. 2025Human Preferences in Large Language Model Latent Space: A Technical Analysis on the Reliability of Synthetic Data in Voting Outcome Predictioncited by 5
  4. 2026Overstating Attitudes, Ignoring Networks: LLM Biases in Simulating Misinformation Susceptibilitycited by 5
  5. 2025From Prediction to Understanding: Will AI Foundation Models Transform Brain Science?cited by 2
  6. 2025Leveraging Interview-Informed LLMs to Model Survey Responses: Comparative Insights from AI-Generated and Human Datacited by 0
  7. 2026Measuring Political Stance and Consistency in Large Language Modelscited by 0
  8. 2026Reasoning Boosts Opinion Alignment in LLMscited by 0
  9. 2026Persona Non Grata: LLM Persona-Driven Generations in MCQA are Unstable in Distinct Dimensionscited by 0
  10. 2026MetaPersona: Task-Grounded Synthetic Populations from Empirical Social Sciencecited by 0