How Proper Scoring Rules Shape LLM Forecasting

Generative AI & LLMs
Published: arXiv: 2608.28482v1
Authors

Benjamin Turtel Paul Wilczewski Kris Skotheim Ville A. Satopää Philip E. Tetlock

Abstract

This paper evaluates how reward function choice shapes the performance and behavior of LLM forecasters. We compare five proper scoring rules as training objectives for binary forecasts of resolved real-world events. Although the rules share the same theoretical incentive for truthful probability reporting, the resulting models differ in calibration, probability use, and estimated profiles of bias, information, and noise, with smaller differences in aggregate accuracy and discrimination. The Brier-trained model has the lowest observed Brier score and highest AUC-ROC, while the log-trained model has the highest observed log score and lowest calibration error. Models with similar aggregate performance also reach that performance through different combinations of bias, information, and noise. Proper scoring rules therefore need not behave interchangeably as training objectives. Reward choice may shape not only how well an LLM forecasts, but how its forecasting errors are structured. Each condition uses a single seed, so some differences may reflect training stochasticity.

Paper Summary

General Summary
This paper addresses important challenges in the field by introducing novel methodologies and approaches. The research contributes to advancing the state-of-the-art and has practical applications that could benefit various domains.
Paper Information
Categories:
cs.LG cs.AI
Published Date:

arXiv ID:

2608.28482v1

Quick Actions