Analyzing the Role of Context in Forecasting with Large Language Models

TL;DR

This paper investigates how context, especially news articles, influences the forecasting accuracy of large language models, revealing that more context improves performance and larger models outperform smaller ones.

Contribution

Introduces a new dataset of binary forecasting questions with related news, and systematically studies the impact of context and model size on forecasting accuracy.

Findings

News articles significantly improve forecasting performance.

Few-shot examples decrease accuracy.

Larger models outperform smaller models.

Abstract

This study evaluates the forecasting performance of recent language models (LLMs) on binary forecasting questions. We first introduce a novel dataset of over 600 binary forecasting questions, augmented with related news articles and their concise question-related summaries. We then explore the impact of input prompts with varying level of context on forecasting performance. The results indicate that incorporating news articles significantly improves performance, while using few-shot examples leads to a decline in accuracy. We find that larger models consistently outperform smaller models, highlighting the potential of LLMs in enhancing automated forecasting.