Analyzing the Role of Context in Forecasting with Large Language Models
This work addresses the challenge of automated forecasting for applications in prediction and decision-making, but it is incremental as it builds on existing LLM capabilities with a new dataset and context analysis.
This study tackled the problem of forecasting with large language models by evaluating their performance on binary forecasting questions, finding that incorporating news articles significantly improved accuracy while few-shot examples reduced it, with larger models consistently outperforming smaller ones.
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.