Saved in:
Bibliographic Details
Main Authors: Ren, Yinuo, Wang, Jue
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.23154
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908427624644608
author Ren, Yinuo
Wang, Jue
author_facet Ren, Yinuo
Wang, Jue
contents This study explores the potential of large language models (LLMs) to enhance expert forecasting through ensemble learning. Leveraging the European Central Bank's Survey of Professional Forecasters (SPF) dataset, we propose a comprehensive framework to evaluate LLM-driven ensemble predictions under varying conditions, including the intensity of expert disagreement, dynamics of herd behavior, and limitations in attention allocation.
format Preprint
id arxiv_https___arxiv_org_abs_2506_23154
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Can LLM Improve for Expert Forecast Combination? Evidence from the European Central Bank Survey
Ren, Yinuo
Wang, Jue
Applications
This study explores the potential of large language models (LLMs) to enhance expert forecasting through ensemble learning. Leveraging the European Central Bank's Survey of Professional Forecasters (SPF) dataset, we propose a comprehensive framework to evaluate LLM-driven ensemble predictions under varying conditions, including the intensity of expert disagreement, dynamics of herd behavior, and limitations in attention allocation.
title Can LLM Improve for Expert Forecast Combination? Evidence from the European Central Bank Survey
topic Applications
url https://arxiv.org/abs/2506.23154