Leveraging Log Probabilities in Language Models to Forecast Future Events

Tommaso Soru, Jim Marshall
1/8/2025
cs.CLcs.LG

No confident code implementation found for this paper. 1 possible match can be shown below.

Abstract

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 1 weaker match is hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Can Language Models Use Forecasting Strategies?

89% match2024

Navigating Tomorrow: Reliably Assessing Large Language Models Performance on Future Event Prediction

87% match2025

Approaching Human-Level Forecasting with Language Models

87% match1 repo132026

PROPHET: An Inferable Future Forecasting Benchmark with Causal Intervened Likelihood Estimation

86% match1 repo102025

Advancing Event Forecasting through Massive Training of Large Language Models: Challenges, Solutions, and Broader Impacts

86% match2025

LLM-as-a-Prophet: Understanding Predictive Intelligence with Prophet Arena

86% match2025

Cite this paper

@article{soru2025leveraging,
  title  = {Leveraging Log Probabilities in Language Models to Forecast Future Events},
  author = {Tommaso Soru and Jim Marshall},
  year   = {2025},
  eprint = {2501.04880},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2501.04880v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2501.04880.svg)](https://codeofpaper.com/paper/2501.04880)

Discussion