SOURCE-LINKED INTELLIGENCE

Competence-Gated Pooling of Language Models and Priors for Event Forecasting

arXiv · AI, language, vision and robotics · article · Sep 10, 2026 · UTC

In hybrid forecasting, a language model is often one of several available signals. A system may already have a market, crowd, or statistical forecast and must decide whether the model adds useful information or should be ignored. The relevant target is therefore not standalone model accuracy, but relative competence, defined as the model's marginal value beyond the available external forecast. Under Brier loss, we characterize when model disagreement can improve an external forecast and derive the gain from using domain-specific rather than global pooling weights. We then introduce a competenc

Read original source ↗ Open in workspace

recordType

paper

region

Global