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

2026-09-10

AI Summary

研究通过引入一个基于领域成果估计的门控机制，来决定语言模型是否对已有预测有边际价值，并据此调整预测权重以提高事件预测准确性。

Abstract

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 competence gate that estimates domain-level source weights from resolved outcomes, shrinks uncertain estimates toward a global weight, and recalibrates the pooled forecast. Across 2,357 resolved binary questions and five language models, the gate improves the main external baseline from 0.0771 to 0.0732 Brier and significantly outperforms global forecast combinations. The gain remains significant under leakage controls and against a leakage-safe time-series prior on the pooled structured set, with separate evidence on FRED. In contrast, the gate gives no significant improvement on the official ForecastBench market subset, where it largely defers to the market. Across four Qwen models, verbal confidence does not reliably identify when the model outperforms the external forecast, while outcome-estimated competence supports better abstention decisions. These results provide a practical approach for selective model use based on measured marginal value.

Problem

• hybrid forecasting
• language model
• external forecast
• marginal value
• relative competence

Innovation

• Competence-Gated Pooling
• Relative Competence
• Brier Loss
• Marginal Value
• Forecast Calibration