Revealing economic facts: LLMs know more than they say

Marcus Buckmann, Quynh Anh Nguyen and Edward Hill

Papers from arXiv.org

Abstract: We investigate whether the hidden states of large language models (LLMs) can be used to estimate and impute economic and financial statistics. Focusing on county-level (e.g. unemployment) and firm-level (e.g. total assets) variables, we show that a simple linear model trained on the hidden states of open-source LLMs outperforms the models' text outputs. This suggests that hidden states capture richer economic information than the responses of the LLMs reveal directly. A learning curve analysis indicates that only a few dozen labelled examples are sufficient for training. We also propose a transfer learning method that improves estimation accuracy without requiring any labelled data for the target variable. Finally, we demonstrate the practical utility of hidden-state representations in super-resolution and data imputation tasks.

Date: 2025-05
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://arxiv.org/pdf/2505.08662 Latest version (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:arx:papers:2505.08662

Access Statistics for this paper

More papers in Papers from arXiv.org
Bibliographic data for series maintained by arXiv administrators ().