Beyond Keywords: Leveraging Generative LLMs and Label Aggregation to Classify Economic Policy Uncertainty in News Articles

A new arXiv paper (arXiv:2609.35856v1) proposes using generative large language models with weak supervision to classify Economic Policy Uncertainty (EPU) in news articles, replacing keyword-based methods that produce high false-positive counts and machine learning approaches that require costly, time-consuming human-labeled data. The study generates synthetic labels through LLM prompting and adds methods for multi-label and hierarchical EPU classification, aiming to make economic monitoring in the public sector more cost-effective and scalable.

arXiv:2609.35856v1 Announce Type: new Abstract: This research describes the adaptation of Large Language Models LLMs for economic monitoring in the public sector to automatically determine whether an article discusses Economic Policy Uncertanity EPU and to identify its specific type. Previous studies either rely on keywords, which often result in a high count of false positives, or use machine learning approaches that require a large number of quality human labeled data that is costly and time consuming to acquire. In this study, we propose approaches based on weak supervision techniques, using generative LLMs to create synthetic labels through prompting, making the approach both cost-effective and scalable. Additionally, we propose methods for for multi-label and hierarchical classification of articles related to EPU.