LLM-Based Measurement of Latent Attributes in Trade Data

Read full text Summarise with VIRAT
Authors: Matthew R DiGiuseppe, Xuelong Fu, Michael E. Flynn
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Trade data are available at a high level of disaggregation, allowing scholars to examine flows of highly specific goods. Yet the sheer number of goods classifications (5,000+) makes it difficult to analyze trade flows and tariff policy at a mid-level of aggregation beyond a few existing categorizations. Here, we outline a method that can scale---not merely classify---traded goods on researcher-defined dimensions that are orthogonal to existing classification schemes. We propose that the embedded knowledge in large language models (LLMs) can be used to conduct pairwise comparisons (PWCs) of Harmonized System (HS) product descriptions by determining their relative proximity to a specific concept. A Bayesian Bradley--Terry model then uses these PWCs to place individual items on a latent scale of interest. These estimates and their associated uncertainty can then be used for downstream descriptive or causal analysis.

Fields of Study & Subjects

Global trade and economics Computational and Text Analysis Methods Topic Modeling

Publication details

Journal / source
SocArXiv (OSF Preprints)
Publication date
27 March 2026
Language
EN
Document type
Preprint