Forecasting Future World Events with Neural Networks

TL;DR

This paper introduces Autocast, a new dataset for forecasting world events using language models, highlighting current limitations and potential improvements in automating complex, real-world predictions.

Contribution

The paper presents Autocast and IntervalQA datasets, enabling evaluation of language models on real-world forecasting tasks with a focus on numerical and event prediction.

Findings

Models perform below human experts in forecasting accuracy.

Increasing model size improves forecasting performance.

Incorporating news data enhances prediction quality.

Abstract

Forecasting future world events is a challenging but valuable task. Forecasts of climate, geopolitical conflict, pandemics and economic indicators help shape policy and decision making. In these domains, the judgment of expert humans contributes to the best forecasts. Given advances in language modeling, can these forecasts be automated? To this end, we introduce Autocast, a dataset containing thousands of forecasting questions and an accompanying news corpus. Questions are taken from forecasting tournaments, ensuring high quality, real-world importance, and diversity. The news corpus is organized by date, allowing us to precisely simulate the conditions under which humans made past forecasts (avoiding leakage from the future). Motivated by the difficulty of forecasting numbers across orders of magnitude (e.g. global cases of COVID-19 in 2022), we also curate IntervalQA, a dataset of numerical questions and metrics for calibration. We test language models on our forecasting task and find that performance is far below a human expert baseline. However, performance improves with increased model size and incorporation of relevant information from the news corpus. In sum, Autocast poses a novel challenge for large language models and improved performance could bring large practical benefits.