paper-with-me

홈 › Papers

Generative AI Voting: Fair Collective Choice is Resilient to LLM Biases and Inconsistencies

2024-05-31 · Srijoni Majumdar, Edith Elkind, Evangelos Pournaras

Scaling up deliberative and voting participation is a longstanding endeavor -- a cornerstone for direct democracy and legitimate collective choice. 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 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 with high realism more than >50K LLM voting personas in 81 real-world voting elections, we disentangle the nature of different biases in LLMS (GPT 3, GPT 3.5, and Llama2). Complex preferential ballot formats exhibit significant inconsistencies compared to simpler majoritarian elections that show higher consistency. Strikingly though, by demonstrating for the first time in real-world a proportional representation of voters in direct democracy, we are also able to show that fair ballot aggregation methods, such as equal shares, prove to be a win-win: fairer voting outcomes for humans with fairer AI representation. This novel underlying relationship proves paramount for democratic resilience in progressives scenarios with low voters turnout and voter fatigue supported by AI representatives: abstained voters are mitigated by recovering highly representative voting outcomes that are fairer. These interdisciplinary insights provide remarkable foundations for science, policymakers, and citizens to develop safeguards and resilience for AI risks in democratic innovations.

📄 PDF Abstract BibTeX arXiv:2406.11871

Code (1)

tdi-lab/generative-ai-voting 공식 구현 tf

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention 설명 없음
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Adam 설명 없음
Linear Warmup With Cosine Annealing Linear Warmup With Cosine Annealing is a learning rate schedule where we increase the learning rate linearly for $n$ updates and then anneal according to a cosine schedule…

Similar Papers 제목 키워드 기반

Fair Voting Methods as a Catalyst for Democratic Resilience: A Trilogy on Legitimacy, Impact and AI Safeguarding

2025-12-19 · Evangelos Pournaras arxiv

This article shows how fair voting methods can be a catalyst for change in the way we make collective decisions, and how such change can promote long-awaited upgrades of democracy. Based on real-world evidence from democ…

Upgrading Democracies with Fairer Voting Methods

2025-05-20 · Evangelos Pournaras, Srijoni Majumdar, Thomas Wellings, Joshua C. Yang 외

Voting methods are instrumental design element of democracies. Citizens use them to express and aggregate their preferences to reach a collective decision. However, voting outcomes can be as sensitive to voting rules as …

LLM Voting: Human Choices and AI Collective Decision Making

2024-01-31 · Joshua C. Yang, Damian Dailisan, Marcin Korecki, Carina I. Hausladen 외

This paper investigates the voting behaviors of Large Language Models (LLMs), specifically GPT-4 and LLaMA-2, their biases, and how they align with human voting patterns. Our methodology involved using a dataset from a h…

Decision MakingDiversity

'Generative CI' through Collective Response Systems

2023-02-01 · Aviv Ovadya

How can many people (who may disagree) come together to answer a question or make a decision? "Collective response systems" are a type of generative collective intelligence (CI) facilitation process meant to address this…

Recommendation Systems

Artificial Delegates Resolve Fairness Issues in Perpetual Voting with Partial Turnout

2025-06-26 · Apurva Shah, Axel Abels, Ann Nowé, Tom Lenaerts

Perpetual voting addresses fairness in sequential collective decision-making by evaluating representational equity over time. However, existing perpetual voting rules rely on full participation and complete approval info…

Decision MakingFairness