Journal of Political Institutions and Political Economy > Vol 6 > Issue 3–4

Can We Measure Legislative Complexity with LLMs?

Austin Bussing, Department of Political Science, Trinity University, USA, Nicholas O. Howard, Department of Political Science, Concordia College, USA, nhoward1@cord.edu , Joshua Y. Lerner, Senior Research Methodologist, NORC at the University of Chicago, USA
 
Suggested Citation
Austin Bussing, Nicholas O. Howard and Joshua Y. Lerner (2025), "Can We Measure Legislative Complexity with LLMs?", Journal of Political Institutions and Political Economy: Vol. 6: No. 3–4, pp 407-426. http://dx.doi.org/10.1561/113.00000130

Publication Date: 01 Oct 2025
© 2025 A. Bussing, N. O. Howard, and J. Y. Lerner
 
Subjects
Lawmaking
 
Keywords
Congresstext analysisLLMcomplexitylegislatures
 

Share

Download article
In this article:
Introduction 
Legislatures, Proposals, and Legislative Complexity 
Understanding and Measuring Complexity 
Data and Methods 
Results 
Discussion 
References 

Abstract

The complexity of legislative language is of theoretical importance to many substantive questions about legislative politics. However, most existing measures of bill complexity are either generated at the broad issue level and applied to individual bills, or they are reliant on a simple metric like length. In this paper, we apply a pairwise comparison framework to the measurement of complexity in legislative texts. We compare the results of a Bradley-Terry model (Bradley and Terry, 1952) fit on pairwise comparisons made by human coders with the results of the same model fit on comparisons made by a large language models (LLMs). There is a moderately high level of agreement between human coders and the LLMs, and the relationships between observable text features and the underlying trait of complexity are similar in comparisons made by human coders and by the LLMs. Our work demonstrates that, with researcher-selected bridging texts and carefully designed prompts, LLMs can be used to measure complexity in legislative texts.

DOI:10.1561/113.00000130

Online Appendix | 113.00000130_app.pdf

This is the article's accompanying appendix.

DOI: 10.1561/113.00000130_app

Companion

Journal of Political Institutions and Political Economy, Volume 6, Issue 3-4 Special Issue: Artificial Intelligence and the Study of Political Institutions
See the other articles that are part of this special issue.