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

arXiv: https://arxiv.org/abs/2410.24190 · HTML: https://mlsanity.com/paper/2410.24190/

## 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 (most cited first, 20 of 20)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [WizardLM: Empowering large pre-trained language models to follow complex instructions](https://mlsanity.com/paper/2304.12244/) (2023)
- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [BERTopic: Neural topic modeling with a class-based TF-IDF procedure](https://mlsanity.com/paper/2203.05794/) (2022)
- [Whose Opinions Do Language Models Reflect?](https://mlsanity.com/paper/2303.17548/) (2023)
- [Improving Alignment and Robustness with Circuit Breakers](https://mlsanity.com/paper/2406.04313/) (2024)
- [From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Models](https://mlsanity.com/paper/2305.08283/) (2023)
- [OpenChat: Advancing Open-source Language Models with Mixed-Quality Data](https://mlsanity.com/paper/2309.11235/) (2023)
- [The political ideology of conversational AI: Converging evidence on ChatGPT's pro-environmental, left-libertarian orientation](https://mlsanity.com/paper/2301.01768/) (2023)
- [A Roadmap to Pluralistic Alignment](https://mlsanity.com/paper/2402.05070/) (2024)
- [SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling](https://mlsanity.com/paper/2312.15166/) (2023)
- [Platypus: Quick, Cheap, and Powerful Refinement of LLMs](https://mlsanity.com/paper/2308.07317/) (2023)
- [Systematic Biases in LLM Simulations of Debates](https://mlsanity.com/paper/2402.04049/) (2024)
- [The Geometry of Culture: Analyzing Meaning through Word Embeddings](https://mlsanity.com/paper/1803.09288/) (2018)
- [The Political Preferences of LLMs](https://mlsanity.com/paper/2402.01789/) (2024)
- [Investigating LLMs as Voting Assistants via Contextual Augmentation: A Case Study on the European Parliament Elections 2024](https://mlsanity.com/paper/2407.08495/) (2024)
- [Aligning AI with Public Values: Deliberation and Decision-Making for Governing Multimodal LLMs in Political Video Analysis](https://mlsanity.com/paper/2410.01817/) (2024)

## Built on by (most cited first, 30 of 71)

- [LLM Social Simulations Are a Promising Research Method](https://mlsanity.com/paper/2504.02234/) (2025)
- [Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs](https://mlsanity.com/paper/2502.08640/) (2025)
- [Persuasion with Large Language Models: A Survey of Empirical Evidence, Study Methodologies, and Ethical Implications](https://mlsanity.com/paper/2411.06837/) (2024)
- [Linear Representations of Political Perspective Emerge in Large Language Models](https://mlsanity.com/paper/2503.02080/) (2025)
- [Emergence of polarization in networks of large language model agents](https://mlsanity.com/paper/2501.05171/) (2025)
- [IssueBench: Millions of Realistic Prompts for Measuring Issue Bias in LLM Writing Assistance](https://mlsanity.com/paper/2502.08395/) (2025)
- [Frontier AI's Impact on the Cybersecurity Landscape](https://mlsanity.com/paper/2504.05408/) (2025)
- [Lies, Damned Lies, and Distributional Language Statistics: Persuasion and Deception with Large Language Models](https://mlsanity.com/paper/2412.17128/) (2024)
- [Beyond Partisan Leaning: A Comparative Analysis of Political Bias in Large Language Models](https://mlsanity.com/paper/2412.16746/) (2024)
- [Persuasion Dynamics in LLMs: Investigating Robustness and Adaptability in Knowledge and Safety with DuET-PD](https://mlsanity.com/paper/2508.17450/) (2025)
- [ToMAP: Training Opponent-Aware LLM Persuaders with Theory of Mind](https://mlsanity.com/paper/2505.22961/) (2025)
- [The Lock-in Hypothesis: Stagnation by Algorithm](https://mlsanity.com/paper/2506.06166/) (2025)
- [HumanAgencyBench: Scalable Evaluation of Human Agency Support in AI Assistants](https://mlsanity.com/paper/2509.08494/) (2025)
- [ValuesRAG: Enhancing Cultural Alignment Through Retrieval-Augmented Contextual Learning](https://mlsanity.com/paper/2501.01031/) (2025)
- [Towards Strategic Persuasion with Language Models](https://mlsanity.com/paper/2509.22989/) (2025)
- [Value Drifts: Tracing Value Alignment During LLM Post-Training](https://mlsanity.com/paper/2510.26707/) (2025)
- [Persuasion Should be Double-Blind: A Multi-Domain Dialogue Dataset With Faithfulness Based on Causal Theory of Mind](https://mlsanity.com/paper/2502.21297/) (2025)
- [Benchmarking Multi-National Value Alignment for Large Language Models](https://mlsanity.com/paper/2504.12911/) (2025)
- [What Is The Political Content in LLMs' Pre- and Post-Training Data?](https://mlsanity.com/paper/2509.22367/) (2025)
- [Benchmarking Overton Pluralism in LLMs](https://mlsanity.com/paper/2512.01351/) (2025)
- [Knowing But Not Doing: Convergent Morality and Divergent Action in LLMs](https://mlsanity.com/paper/2601.07972/) (2026)
- [B-score: Detecting biases in large language models using response history](https://mlsanity.com/paper/2505.18545/) (2025)
- [Geopolitical biases in LLMs: what are the "good" and the "bad" countries according to contemporary language models](https://mlsanity.com/paper/2506.06751/) (2025)
- [Do Political Opinions Transfer Between Western Languages? An Analysis of Unaligned and Aligned Multilingual LLMs](https://mlsanity.com/paper/2508.05553/) (2025)
- [When Correct Beliefs Collapse: Epistemic Resilience of LLMs under Clinical Pressure](https://mlsanity.com/paper/2605.23932/) (2026)
- [Political Ideology Shifts in Large Language Models](https://mlsanity.com/paper/2508.16013/) (2025)
- [SocialHarmBench: Revealing LLM Vulnerabilities to Socially Harmful Requests](https://mlsanity.com/paper/2510.04891/) (2025)
- [AI-Enhanced Deliberative Democracy and the Future of the Collective Will](https://mlsanity.com/paper/2503.05830/) (2025)
- ["I understand your perspective": LLM Persuasion through the Lens of Communicative Action Theory](https://mlsanity.com/paper/2606.08076/) (2026)
- [A Detailed Factor Analysis for the Political Compass Test: Navigating Ideologies of Large Language Models](https://mlsanity.com/paper/2506.22493/) (2025)

## 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.