The paper examines how Preference Inference (PI) models used in large-scale participatory democracy platforms can alter the perceived consensus and minority support by predicting missing votes. It introduces a collective‑centric evaluation framework that assesses whether inferred votes maintain key properties of the overall preference landscape, rather than focusing solely on individual prediction accuracy. Using the largest multilingual dataset to date—four consultations with over 90,000 participants, 1 million votes, and 22 languages—the study finds that models with similar predictive accuracy can differ markedly in how well they preserve the collective structure, underscoring that accuracy alone is insufficient for evaluating PI in democratic contexts.
arXiv:2606. 28294v1 Announce Type: new Abstract: Preference-based alignment often struggles to capture the reasoning that underlies human judgments.
The paper argues that AI can strengthen democracy by supporting large‑scale deliberation, addressing cognitive, social, platform‑design, and market frictions while preserving human agency. It contrasts AI‑assisted deliberation with liquid democracy, claiming the former lowers barriers to meaningful engagement without replacing human judgment. The authors outline four guiding principles—preserving agency, encouraging mutual respect, promoting equality, and augmenting active citizenship—and discuss challenges such as alignment, sycophancy, bias, and over‑reliance. They call on the machine learning community to develop and evaluate deliberation‑focused AI systems based on their ability to facilitate informed, representative, and friction‑robust discourse.
The paper examines whether AI‑driven debate can help humans and weaker language models (LLMs) correct their judgments. Experiments show that debate improves human accuracy over prior beliefs, especially with weighted voting, but offers little benefit—and sometimes harms—accuracy for weaker LLM supervisors. The study highlights debate as a promising tool for scalable human oversight while questioning its effectiveness for fully automated AI control.
AI systems can strengthen democracy by supporting deliberation at scale by addressing cognitive, social, platform-design, and market-driven frictions, while preserving human agency. Unlike proposals s...
arXiv:2607. 15095v1 Announce Type: cross Abstract: The formation of political coalitions is a complex negotiation driven by both concrete policy objectives and deep-seated ideological convictions.
arXiv:2603. 23841v2 Announce Type: replace-cross Abstract: While Large Language Models (LLMs) are increasingly used as primary sources of information, their potential for political bias may impact their objectivity.
The paper examines how large language models (LLMs) emulate voters in digital democracy and the demographic biases that arise. By analyzing three U.S. presidential elections, the authors compare a closed‑source and an open‑source LLM, finding that removing gender or education from voter profiles can significantly reduce group errors, while removing race increases errors. Common alignment tactics such as repeated queries or fairness instructions fail to mitigate these disparities and can even worsen them.
arXiv:2609.22497v1 Announce Type: new Abstract: The aggregation of many lay estimates often outperforms individual expert judgment, a phenomenon known as the wisdom of crowds. While this is usually a...
The paper introduces Radial Consensus Score (RCS), a training‑free method for selecting the best answer from a set of candidate responses generated by large language models. RCS computes a weighted Fréchet mean of answer embeddings to form a semantic center and ranks candidates by their radial distance to this center, thereby capturing semantic consistency rather than surface agreement. Experiments on five open‑weight models and multiple benchmarks show that RCS matches or surpasses strong baselines across all sampling budgets, especially when correct answers are lexically fragmented, and can replace majority voting in multi‑agent debate and black‑box settings.
arXiv:2609.15207v1 Announce Type: new Abstract: Generative AI writing assistants and the Large Language Models (LLMs) that power them are increasingly part of how voters gather information before ele...
The paper investigates how to detect enthymemes—arguments with unstated premises or conclusions—in controversial political tweets about vaccination and immigration. Despite extensive fine‑tuning, models achieve an F1 score of only about 0.67, prompting the authors to propose new evaluation metrics that compare predictions to the full distribution of annotator votes and a model that directly predicts this distribution. The study also shows that models rely on explicit argumentative structure, often missing implicit links that readers must infer, raising concerns for content moderation systems that depend on majority labels.
MABPD (Multi‑Agent Bias Probing & Detection) is a training‑free pipeline that uses three specialized large language model agents to analyze news articles from complementary perspectives and resolve disagreements via a Structured Argument Debate (SAD) protocol. SAD imposes an asymmetric burden of proof—biased claims lacking grounded textual evidence receive zero weight—along with role‑weighted voting and post‑consensus verification, replacing task‑specific supervised decision boundaries. Ablation studies show that the debate module alone accounts for up to a 10.6‑point F1 gain, and on the BABE benchmark MABPD attains 83.4% macro F1, within 0.7 percentage points of the supervised state‑of‑the‑art, while achieving 75.0% zero‑shot accuracy on the SemEval 2019 HyperPartisan corpus.