Saved in:
Bibliographic Details
Main Authors: Karkar, Chinmay, Chopra, Paras
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.18394
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911283084787712
author Karkar, Chinmay
Chopra, Paras
author_facet Karkar, Chinmay
Chopra, Paras
contents Large Language Models (LLMs) demonstrate partial forecasting competence across social, political, and economic events. Yet, their predictive ability varies sharply with domain structure and prompt framing. We investigate how forecasting performance varies with different model families on real-world questions about events that happened beyond the model cutoff date. We analyze how context, question type, and external knowledge affect accuracy and calibration, and how adding factual news context modifies belief formation and failure modes. Our results show that forecasting ability is highly variable as it depends on what, and how, we ask.
format Preprint
id arxiv_https___arxiv_org_abs_2511_18394
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Future Is Unevenly Distributed: Forecasting Ability of LLMs Depends on What We're Asking
Karkar, Chinmay
Chopra, Paras
Machine Learning
Large Language Models (LLMs) demonstrate partial forecasting competence across social, political, and economic events. Yet, their predictive ability varies sharply with domain structure and prompt framing. We investigate how forecasting performance varies with different model families on real-world questions about events that happened beyond the model cutoff date. We analyze how context, question type, and external knowledge affect accuracy and calibration, and how adding factual news context modifies belief formation and failure modes. Our results show that forecasting ability is highly variable as it depends on what, and how, we ask.
title Future Is Unevenly Distributed: Forecasting Ability of LLMs Depends on What We're Asking
topic Machine Learning
url https://arxiv.org/abs/2511.18394