mlsanityData to 14 Oct 2026

Hidden Persuaders: LLMs' Political Leaning and Their Influence on Voters

arXiv 2410.24190 ↗First posted 31 Oct 2024cs.CL cs.CYcited by 71

Not on the map. Why?

Abstract (arXiv)

How could LLMs influence our democracy? We investigate LLMs' political leanings and the potential influence of LLMs on voters by conducting multiple experiments in a U.S. presidential election context. Through a voting simulation, we first demonstrate 18 open- and closed-weight LLMs' political preference for a Democratic nominee over a Republican nominee. We show how this leaning towards the Democratic nominee becomes more pronounced in instruction-tuned models compared to their base versions by analyzing their responses to candidate-policy related questions. We further explore the potential impact of LLMs on voter choice by conducting an experiment with 935 U.S. registered voters. During the experiments, participants interacted with LLMs (Claude-3, Llama-3, and GPT-4) over five exchanges. The experiment results show a shift in voter choices towards the Democratic nominee following LLM interaction, widening the voting margin from 0.7% to 4.6%, even though LLMs were not asked to persuade users to support the Democratic nominee during the discourse. This effect is larger than many previous studies on the persuasiveness of political campaigns, which have shown minimal effects in presidential elections. Many users also expressed a desire for further political interaction with LLMs. Which aspects of LLM interactions drove these shifts in voter choice requires further study. Lastly, we explore how a safety method can make LLMs more politically neutral, while raising the question of whether such neutrality is truly the path forward.

Key facts. Cited by 71 papers in the map (data through 14 Oct 2026). Builds on 20 of its 72 references that are in the map. First posted on arXiv 31 Oct 2024.

Builds on

20 of 72 references.

References · 20

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2022Training language models to follow instructions with human feedbackcited by 15,971
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  4. 2023Representation Engineering: A Top-Down Approach to AI Transparencycited by 1,336
  5. 2023WizardLM: Empowering large pre-trained language models to follow complex instructionscited by 1,125
  6. 2023Towards Understanding Sycophancy in Language Modelscited by 1,040
  7. 2022BERTopic: Neural topic modeling with a class-based TF-IDF procedurecited by 801
  8. 2023Whose Opinions Do Language Models Reflect?cited by 773
  9. 2024Improving Alignment and Robustness with Circuit Breakerscited by 322
  10. 2023From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Modelscited by 260
  11. 2023OpenChat: Advancing Open-source Language Models with Mixed-Quality Datacited by 252
  12. 2023The political ideology of conversational AI: Converging evidence on ChatGPT's pro-environmental, left-libertarian orientationcited by 189
8 more
  1. 2024A Roadmap to Pluralistic Alignmentcited by 184
  2. 2023SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scalingcited by 172
  3. 2023Platypus: Quick, Cheap, and Powerful Refinement of LLMscited by 150
  4. 2024Systematic Biases in LLM Simulations of Debatescited by 99
  5. 2018The Geometry of Culture: Analyzing Meaning through Word Embeddingscited by 87
  6. 2024The Political Preferences of LLMscited by 84
  7. 2024Investigating LLMs as Voting Assistants via Contextual Augmentation: A Case Study on the European Parliament Elections 2024cited by 7
  8. 2024Aligning AI with Public Values: Deliberation and Decision-Making for Governing Multimodal LLMs in Political Video Analysiscited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 40; 2026: 28.

71 papers.

Sort:

By area:

  1. 2025LLM Social Simulations Are a Promising Research Methodcited by 99
  2. 2025Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIscited by 67
  3. 2024Persuasion with Large Language Models: A Survey of Empirical Evidence, Study Methodologies, and Ethical Implicationscited by 32
  4. 2025Linear Representations of Political Perspective Emerge in Large Language Modelscited by 32
  5. 2025Emergence of polarization in networks of large language model agentscited by 26
  6. 2025IssueBench: Millions of Realistic Prompts for Measuring Issue Bias in LLM Writing Assistancecited by 26
  7. 2025Frontier AI's Impact on the Cybersecurity Landscapecited by 21
  8. 2024Lies, Damned Lies, and Distributional Language Statistics: Persuasion and Deception with Large Language Modelscited by 15
  9. 2024Beyond Partisan Leaning: A Comparative Analysis of Political Bias in Large Language Modelscited by 13
  10. 2025Persuasion Dynamics in LLMs: Investigating Robustness and Adaptability in Knowledge and Safety with DuET-PDcited by 13
  11. 2025ToMAP: Training Opponent-Aware LLM Persuaders with Theory of Mindcited by 12
  12. 2025The Lock-in Hypothesis: Stagnation by Algorithmcited by 11
38 more
  1. 2025HumanAgencyBench: Scalable Evaluation of Human Agency Support in AI Assistantscited by 11
  2. 2025ValuesRAG: Enhancing Cultural Alignment Through Retrieval-Augmented Contextual Learningcited by 10
  3. 2025Towards Strategic Persuasion with Language Modelscited by 10
  4. 2025Value Drifts: Tracing Value Alignment During LLM Post-Trainingcited by 10
  5. 2025Persuasion Should be Double-Blind: A Multi-Domain Dialogue Dataset With Faithfulness Based on Causal Theory of Mindcited by 8
  6. 2025Benchmarking Multi-National Value Alignment for Large Language Modelscited by 7
  7. 2025What Is The Political Content in LLMs' Pre- and Post-Training Data?cited by 7
  8. 2025Benchmarking Overton Pluralism in LLMscited by 7
  9. 2026Knowing But Not Doing: Convergent Morality and Divergent Action in LLMscited by 7
  10. 2025B-score: Detecting biases in large language models using response historycited by 6
  11. 2025Geopolitical biases in LLMs: what are the "good" and the "bad" countries according to contemporary language modelscited by 6
  12. 2025Do Political Opinions Transfer Between Western Languages? An Analysis of Unaligned and Aligned Multilingual LLMscited by 6
  13. 2026When Correct Beliefs Collapse: Epistemic Resilience of LLMs under Clinical Pressurecited by 6
  14. 2025Political Ideology Shifts in Large Language Modelscited by 5
  15. 2025SocialHarmBench: Revealing LLM Vulnerabilities to Socially Harmful Requestscited by 5
  16. 2025AI-Enhanced Deliberative Democracy and the Future of the Collective Willcited by 4
  17. 2026"I understand your perspective": LLM Persuasion through the Lens of Communicative Action Theorycited by 4
  18. 2025A Detailed Factor Analysis for the Political Compass Test: Navigating Ideologies of Large Language Modelscited by 3
  19. 2025How large language models judge and influence human cooperationcited by 3
  20. 2025From Noise to Signal to Selbstzweck: Reframing Human Label Variation in the Era of Post-training in NLPcited by 3
  21. 2026Architecting Trust in Artificial Epistemic Agentscited by 3
  22. 2026Political Bias Audits of LLMs Capture Sycophancy to the Inferred Auditorcited by 3
  23. 2025The potential -- and the pitfalls -- of using pre-trained language models as cognitive science theoriescited by 2
  24. 2025Analysis of LLM Bias (Chinese Propaganda & Anti-US Sentiment) in DeepSeek-R1 vs. ChatGPT o3-mini-highcited by 2
  25. 2026Structuring the Space of Sociotechnical Alignmentcited by 2
  26. 2025Working with Large Language Models to Enhance Messaging Effectiveness for Vaccine Confidencecited by 1
  27. 2025How Persuasive Could LLMs Be? A First Study Combining Linguistic-Rhetorical Analysis and User Experimentscited by 1
  28. 2025The Hunger Game Debate: On the Emergence of Over-Competition in Multi-Agent Systemscited by 1
  29. 2026Large Language Models Persuade Without Planning Theory of Mindcited by 1
  30. 2026How AI Systems Think About Education: Analyzing Latent Preference Patterns in Large Language Modelscited by 1
  31. 2026Distributional Open-Ended Evaluation of LLM Cultural Value Alignment Based on Value Codebookcited by 1
  32. 2026AI-Mediated Communication Can Steer Collective Opinioncited by 1
  33. 2025Embracing Dialectic Intersubjectivity: Coordination of Different Perspectives in Content Analysis with LLM Persona Simulationcited by 0
  34. 2025LLMs' Leaning in European Electionscited by 0
  35. 2025Through the LLM Looking Glass: A Socratic Probing of Donkeys, Elephants, and Marketscited by 0
  36. 2025Persona-driven Simulation of Voting Behavior in the European Parliament with Large Language Modelscited by 0
  37. 2025Benchmarking Gender and Political Bias in Large Language Modelscited by 0
  38. 2025From Ground Trust to Truth: Disparities in Offensive Language Judgments on Contemporary Korean Political Discoursecited by 0

50 most cited of 71 All 71 (JSON)