The Wisdom of Artificial Deliberative Crowds

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 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 previously used with human participants for use with large language models from three different families, and test it across four domains of increasing real-world stakes: visual numerical estimation (Study 1), peer review of machine-learning papers (Study 2), detection of hidden malicious behavior by an artificial intelligence agent (Study 3), and sports forecasting against a real prediction market (Study 4). Across domains, deliberation reduced collective error beyond passive aggregation of independent responses, and post-deliberation individual judgments retained this collective gain. Notably, the advantage required model diversity: groups composed of clones of a single model did not benefit from deliberating. These results establish machine deliberation as a general-purpose aggregation mechanism, and point to diversity as an active ingredient.

Study shows deliberation improves accuracy in language models.

SOURCE     arXiv cs.AI (tier 1)
   ↓
DOCUMENT   0072be17-92c5-432a-baf0-f849eec50a9d
           https://arxiv.org/abs/2609.22497
   ↓
EVIDENCE   2 extracted excerpts
   ↓
MODEL RUN  1 run, methodology 1.0.1
   ↓
SCORE      +50  (Favourable)
   ↓
CONFIDENCE 80%