« Back to Results

Using AI to Measure Economic Dynamics

Paper Session

Saturday, Jan. 3, 2026 8:00 AM - 10:00 AM (EST)

Philadelphia Marriott Downtown
Hosted By: American Economic Association
  • Chair: Martin Uribe, Columbia University and NBER

An Anatomy of Firms’ Political Speech

Pablo Ottonello
,
University of Maryland and NBER
Wenting Song
,
University of California-Davis
Sebastian Sotelo
,
University of Michigan and NBER

Abstract

We study the distribution of political speech across U.S. firms, using large language models to measure political engagement in firms’ communications. Our analysis reveals five facts: (1) Political engagement is rare. (2) It is concentrated among large firms. (3) Firms specialize in specific topics and outlets. (4) Large firms engage in a broader set of topics and outlets. (5) The 2020 surge in political engagement was associated with increased engagement by medium-sized firms and a shift in political topics. These findings suggest fixed costs to political engagement and the dominance of large firms’ views in the political space.

Redrawing the Landscape of Cross-Border Flow Restrictions: Modern Tools and Historical Perspectives

Katharina Bergant
,
International Monetary Fund
Andres Fernandez
,
International Monetary Fund
Ken Teoh
,
International Monetary Fund
Martin Uribe
,
Columbia University and NBER

Abstract

We utilize large language models to analyze semi-structured official documents, providing a detailed and comprehensive account of daily de jure restrictions on balance of payment flows worldwide, over the past seven decades, since the inception of the Bretton Woods system. Our analysis uncovers the diverse instruments used to limit cross-border flows and their evolving prevalence over time. The granularity of the new measures we develop enables us to document variations in the use of these instruments across eight categories of restrictions, as well as other key dimensions such as the direction of restricted flows (inflows or outflows), the type of restriction (e.g., price-based versus non-price-based), and the countries’ level of economic development. Additionally, we explore the motivations articulated by policymakers for adopting specific restrictions and quantify the real effects of these measures using the new high-frequency data.

The Value of Worker Rights in Collective Bargaining

Benjamin Arold
,
University of Cambridge
Elliott Ash
,
ETH Zurich and CEPR
W. Bentley MacLeod
,
Yale University and NBER
Suresh Naidu
,
Columbia University and NBER

Abstract

This paper proposes novel natural language methods to measure worker rights from collective bargaining agreements (CBAs) for use in empirical economic analysis. Applying unsupervised text-as-data algorithms to a new collection of 30,000 CBAs from Canada in the period 1986-2015, we parse legal obligations (e.g., “the employer shall provide...”) and legal rights (e.g., “workers shall receive...”) from the contract text. We validate that contract clauses provide worker rights, which include both amenities and control over the work environment. Companies that provide more worker rights score highly on a survey indicating pro-worker management practices. Using time-varying province-level variation in labor income tax rates, we find that higher taxes increase the share of worker-rights clauses while reducing pre-tax wages in unionized firms, consistent with a substitution effect away from taxed compensation (wages) toward untaxed amenities (worker rights). Further, an exogenous increase in the value of outside options (from a leave-one-out instrument for labor demand) increases the share of worker rights clauses in CBAs. Combining the regression estimates, we infer that a one-standard-deviation increase in worker rights is valued at about 5.7% of wages.

Reading the Fund: A Systematic Analysis of IMF Fiscal Advice using LLMs

Anton Korinek
,
University of Virginia and NBER and CEPR
Jeremie Cohen-Setton
,
International Monetary Fund
Jantsankhorloo Amgalan
,
International Monetary Fund

Abstract

This paper presents a systematic analysis of the International Monetary Fund’s (IMF) fiscal policy advice using large language models (LLMs). Leveraging recent advances in natural language processing, we construct a novel framework to extract, classify, and evaluate the content and evolution of IMF fiscal recommendations across a comprehensive corpus of Article IV reports and program documents. Our methodology employs LLMs that allow for the automated identification of key themes, shifts in policy emphasis, and the alignment of advice with country-specific macroeconomic conditions. The analysis reveals patterns in the Fund’s fiscal guidance and subsequent policy actions in the corresponding member countries. We demonstrate that LLMs, when systematically aligned with domain-specific knowledge and historical experience, can provide valuable insights into the consistency, pragmatism, and contextualization of IMF fiscal advice.

Discussant(s)
Aakash Kalyani
,
Federal Reserve Bank of St. Louis
Anton Korinek
,
University of Virginia
Thomas Drechsel
,
University of Maryland
Paul E. Soto
,
Federal Reserve Board
JEL Classifications
  • A1 - General Economics
  • E6 - Macroeconomic Policy, Macroeconomic Aspects of Public Finance, and General Outlook