# Generative AI voting: fair collective choice is resilient to LLM biases and inconsistencies

arXiv: https://arxiv.org/abs/2406.11871 · HTML: https://mlsanity.com/paper/2406.11871/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 101 references that are in the map.
- First posted on arXiv 31 May 2024.

## Builds on (most cited first, 28 of 28)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Out of One, Many: Using Language Models to Simulate Human Samples](https://mlsanity.com/paper/2209.06899/) (2022)
- [In-Context Retrieval-Augmented Language Models](https://mlsanity.com/paper/2302.00083/) (2023)
- [Explainability for Large Language Models: A Survey](https://mlsanity.com/paper/2309.01029/) (2023)
- [Detecting and Preventing Hallucinations in Large Vision Language Models](https://mlsanity.com/paper/2308.06394/) (2023)
- [Bias in Machine Learning Software: Why? How? What to do?](https://mlsanity.com/paper/2105.12195/) (2021)
- [GPTEval: A Survey on Assessments of ChatGPT and GPT-4](https://mlsanity.com/paper/2308.12488/) (2023)
- [Generative Social Choice](https://mlsanity.com/paper/2309.01291/) (2023)
- [Opportunities and Risks of LLMs for Scalable Deliberation with Polis](https://mlsanity.com/paper/2306.11932/) (2023)
- [Proportional Participatory Budgeting with Additive Utilities](https://mlsanity.com/paper/2008.13276/) (2020)
- [Participatory Budgeting: Models and Approaches](https://mlsanity.com/paper/2003.00606/) (2020)
- [BASED-XAI: Breaking Ablation Studies Down for Explainable Artificial Intelligence](https://mlsanity.com/paper/2207.05566/) (2022)
- [Participatory Budgeting: Data, Tools, and Analysis](https://mlsanity.com/paper/2305.11035/) (2023)
- [Phragm'en's Voting Methods and Justified Representation](https://mlsanity.com/paper/2102.12305/) (2021)
- [Taming the Cross Entropy Loss](https://mlsanity.com/paper/1810.05075/) (2018)
- [Proof of Witness Presence: Blockchain Consensus for Augmented Democracy in Smart Cities](https://mlsanity.com/paper/1907.00498/) (2019)
- [Fairkit, Fairkit, on the Wall, Who's the Fairest of Them All? Supporting Data Scientists in Training Fair Models](https://mlsanity.com/paper/2012.09951/) (2020)
- [Designing Digital Voting Systems for Citizens: Achieving Fairness and Legitimacy in Participatory Budgeting](https://mlsanity.com/paper/2310.03501/) (2023)
- [Feature Importance in Gradient Boosting Trees with Cross-Validation Feature Selection](https://mlsanity.com/paper/2109.05468/) (2021)
- [How Value-Sensitive Design Can Empower Sustainable Consumption](https://mlsanity.com/paper/2004.09180/) (2020)
- [Participatory Budgeting with Cumulative Votes](https://mlsanity.com/paper/2009.02690/) (2020)
- [Understanding Political Divisiveness using Online Participation data from the 2022 French and Brazilian Presidential Elections](https://mlsanity.com/paper/2211.04577/) (2022)
- [Fair and Inclusive Participatory Budgeting: Voter Experience with Cumulative and Quadratic Voting Interfaces](https://mlsanity.com/paper/2308.04345/) (2023)
- [Science in the Era of ChatGPT, Large Language Models and Generative AI: Challenges for Research Ethics and How to Respond](https://mlsanity.com/paper/2305.15299/) (2023)
- [Fair Voting Outcomes with Impact and Novelty Compromises? Unraveling Biases in Electing Participatory Budgeting Winners](https://mlsanity.com/paper/2405.05085/) (2024)
- [Consensus-based Participatory Budgeting for Legitimacy: Decision Support via Multi-agent Reinforcement Learning](https://mlsanity.com/paper/2307.12915/) (2023)

## Built on by (most cited first, 8 of 8)

- [Political Actor Agent: Simulating Legislative System for Roll Call Votes Prediction with Large Language Models](https://mlsanity.com/paper/2412.07144/) (2024)
- [CrowdLLM: Building LLM-Based Digital Populations Augmented with Generative Models](https://mlsanity.com/paper/2512.07890/) (2025)
- [Distribution-Aware Reward Estimation for Test-Time Reinforcement Learning](https://mlsanity.com/paper/2601.21804/) (2026)
- [Upgrading Democracies with Fairer Voting Methods](https://mlsanity.com/paper/2505.14349/) (2025)
- [Prompt Injection Vulnerability of Consensus Generating Applications in Digital Democracy](https://mlsanity.com/paper/2508.04281/) (2025)
- [Fair Voting Methods as a Catalyst for Democratic Resilience: A Trilogy on Legitimacy, Impact and AI Safeguarding](https://mlsanity.com/paper/2512.17461/) (2025)
- [Democracy in the Era of Artificial Intelligence](https://mlsanity.com/paper/2606.13026/) (2026)
- [Collective Bias Mitigation via Model Routing and Collaboration](https://mlsanity.com/paper/2610.03240/) (2026)

## Abstract (arXiv)

Recent breakthroughs in generative artificial intelligence (AI) and large language models (LLMs) unravel new capabilities for AI personal assistants to overcome cognitive bandwidth limitations of humans, providing decision support or even direct representation of abstained human voters at large scale. However, the quality of this representation and what underlying biases manifest when delegating collective decision making to LLMs is an alarming and timely challenge to tackle. By rigorously emulating more than >50K LLM voting personas in 363 real-world voting elections, we disentangle how AI-generated choices differ from human choices and how this affects collective decision outcomes. Complex preferential ballot formats show significant inconsistencies compared to simpler majoritarian elections, which demonstrate higher consistency. Strikingly, proportional ballot aggregation methods such as equal shares prove to be a win-win: fairer voting outcomes for humans and fairer AI representation, especially for voters likely to abstain. This novel underlying relationship proves paramount for building democratic resilience in scenarios of low voters turnout by voter fatigue: abstained voters are mitigated via AI representatives that recover representative and fair voting outcomes. These interdisciplinary insights provide decision support to policymakers and citizens for developing safeguards and policies for risks of using AI in democratic innovations.