mlsanityData to 14 Oct 2026

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

arXiv 2406.11871 ↗First posted 31 May 2024cs.AIcited by 8

Not on the map. Why?

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.

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

28 of 101 references.

References · 28

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  3. 2019The Curious Case of Neural Text Degenerationcited by 2,916
  4. 2022Out of One, Many: Using Language Models to Simulate Human Samplescited by 752
  5. 2023In-Context Retrieval-Augmented Language Modelscited by 702
  6. 2023Explainability for Large Language Models: A Surveycited by 333
  7. 2023Detecting and Preventing Hallucinations in Large Vision Language Modelscited by 256
  8. 2021Bias in Machine Learning Software: Why? How? What to do?cited by 93
  9. 2023GPTEval: A Survey on Assessments of ChatGPT and GPT-4cited by 73
  10. 2023Generative Social Choicecited by 43
  11. 2023Opportunities and Risks of LLMs for Scalable Deliberation with Poliscited by 42
  12. 2020Proportional Participatory Budgeting with Additive Utilitiescited by 37
16 more
  1. 2020Participatory Budgeting: Models and Approachescited by 23
  2. 2022BASED-XAI: Breaking Ablation Studies Down for Explainable Artificial Intelligencecited by 13
  3. 2023Participatory Budgeting: Data, Tools, and Analysiscited by 13
  4. 2021Phragm'en's Voting Methods and Justified Representationcited by 12
  5. 2018Taming the Cross Entropy Losscited by 10
  6. 2019Proof of Witness Presence: Blockchain Consensus for Augmented Democracy in Smart Citiescited by 9
  7. 2020Fairkit, Fairkit, on the Wall, Who's the Fairest of Them All? Supporting Data Scientists in Training Fair Modelscited by 9
  8. 2023Designing Digital Voting Systems for Citizens: Achieving Fairness and Legitimacy in Participatory Budgetingcited by 9
  9. 2021Feature Importance in Gradient Boosting Trees with Cross-Validation Feature Selectioncited by 6
  10. 2020How Value-Sensitive Design Can Empower Sustainable Consumptioncited by 5
  11. 2020Participatory Budgeting with Cumulative Votescited by 4
  12. 2022Understanding Political Divisiveness using Online Participation data from the 2022 French and Brazilian Presidential Electionscited by 4
  13. 2023Fair and Inclusive Participatory Budgeting: Voter Experience with Cumulative and Quadratic Voting Interfacescited by 3
  14. 2023Science in the Era of ChatGPT, Large Language Models and Generative AI: Challenges for Research Ethics and How to Respondcited by 2
  15. 2024Fair Voting Outcomes with Impact and Novelty Compromises? Unraveling Biases in Electing Participatory Budgeting Winnerscited by 2
  16. 2023Consensus-based Participatory Budgeting for Legitimacy: Decision Support via Multi-agent Reinforcement Learningcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 4; 2026: 3.

8 papers.

  1. 2024Political Actor Agent: Simulating Legislative System for Roll Call Votes Prediction with Large Language Modelscited by 6
  2. 2025CrowdLLM: Building LLM-Based Digital Populations Augmented with Generative Modelscited by 5
  3. 2026Distribution-Aware Reward Estimation for Test-Time Reinforcement Learningcited by 3
  4. 2025Upgrading Democracies with Fairer Voting Methodscited by 2
  5. 2025Prompt Injection Vulnerability of Consensus Generating Applications in Digital Democracycited by 2
  6. 2025Fair Voting Methods as a Catalyst for Democratic Resilience: A Trilogy on Legitimacy, Impact and AI Safeguardingcited by 1
  7. 2026Democracy in the Era of Artificial Intelligencecited by 0
  8. 2026Collective Bias Mitigation via Model Routing and Collaborationcited by 0