Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2501.04880 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915095607508992 |
|---|---|
| author | Soru, Tommaso Marshall, Jim |
| author_facet | Soru, Tommaso Marshall, Jim |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_04880 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Leveraging Log Probabilities in Language Models to Forecast Future Events Soru, Tommaso Marshall, Jim Computation and Language Machine Learning 60-08 I.2.3; I.2.7 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. |
| title | Leveraging Log Probabilities in Language Models to Forecast Future Events |
| topic | Computation and Language Machine Learning 60-08 I.2.3; I.2.7 |
| url | https://arxiv.org/abs/2501.04880 |