arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2501.04880cs.CLcs.LG
收藏

利用语言模型中的对数概率预测未来事件

Leveraging Log Probabilities in Language Models to Forecast Future Events

Serendipity AI Ltd.(Serendipity AI有限公司)

Tommaso Soru, Jim Marshall

AI总结:

本文提出利用 LLM 的对数概率进行多步骤概率估计,结合当前趋势数据预测15个主题的未来事件,Brier 分数显著优于随机猜测和通用 AI 系统。

摘要:

在不断变化的数据驱动决策领域,准确预测未来事件对于多个行业的战略规划至关重要。大型语言模型(LLM)的出现标志着这一领域的重大进展,它们提供了利用海量文本数据进行预测的先进工具。在这篇行业论文中,我们介绍了一种使用 LLM 进行 AI 驱动前瞻的新方法。在以往研究的基础上,我们利用有关当前趋势及其轨迹的数据,对15个不同主题生成预测。随后,我们通过一种基于对数概率的多步骤方法估计这些预测的概率。我们展示了所获 Brier 分数为0.186,这意味着相较随机概率提升26%,相较广泛可用的 AI 系统提升19%。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑