用大模型对数概率预测未来事件，准确率显著优于随机猜测和现有AI系统。
Leveraging Log Probabilities in Language Models to Forecast Future Events
- 基于当前趋势数据与多步对数概率估算，构建事件预测方法。
- 在15个主题上实现0.186的Brier得分，比随机猜测高26%。
- 适合需要前瞻性分析的决策者，尤其关注可量化趋势预测场景。
在数据驱动决策不断演进的背景下，准确预测未来事件对各领域的战略规划至关重要。大型语言模型（LLMs）的兴起为此提供了重要工具，能利用海量文本数据进行预测。本文提出一种基于LLM的AI前瞻性预测新方法。在已有研究基础上，我们采用当前趋势及其演变轨迹数据，对15个不同主题生成预测，并通过基于对数概率的多步方法估算其发生概率。实验表明，该方法达到0.186的Brier分数，相较于随机猜测提升26%，相比广泛可用的AI系统提升19%。
原文摘要 · Abstract (English)
In the constantly changing field of data-driven decision making, accurately predicting future events is crucial for strategic planning in various sectors. The emergence of Large Language Models (LLMs) marks a significant advancement in this area, offering advanced tools that utilise extensive text data for prediction. In this industry paper, we introduce a novel method for AI-driven foresight using LLMs. Building on top of previous research, we employ data on current trends and their trajectories for generating forecasts on 15 different topics. Subsequently, we estimate their probabilities via a multi-step approach based on log probabilities. We show we achieve a Brier score of 0.186, meaning a +26% improvement over random chance and a +19% improvement over widely-available AI systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。