SOURCE-LINKED INTELLIGENCE

The Wisdom of Artificial Deliberative Crowds

arXiv · AI, language, vision and robotics · article · Sep 18, 2026 · UTC

The aggregation of many lay estimates often outperforms individual expert judgment, a phenomenon known as the wisdom of crowds. While this is usually attributed to the independence of estimates, an even stronger effect arises through deliberation: averaging the consensus estimates of small deliberating groups outperforms the classical wisdom of crowds, with individual judgments themselves also becoming more accurate after deliberation. Whether these improvements transfer to large language models deliberating amongst themselves is unknown. Here we adapt a three-stage deliberation paradigm previ

Read original source ↗ Open in workspace

recordType

paper

region

Global