Enhancing Document Retrieval in COVID-19 Research: Leveraging Large Language Models for Hidden Relation Extraction

TL;DR

This paper introduces Covrelex-SE, a system that uses large language models to extract hidden relationships from COVID-19 publications, improving document retrieval quality during pandemics.

Contribution

The paper presents a novel approach leveraging large language models to extract hidden relations in unlabeled COVID-19 research publications, enhancing retrieval accuracy.

Findings

Improved retrieval results with LLM-based relation extraction

Enhanced identification of hidden relationships in publications

Better support for COVID-19 research queries

Abstract

In recent years, with the appearance of the COVID-19 pandemic, numerous publications relevant to this disease have been issued. Because of the massive volume of publications, an efficient retrieval system is necessary to provide researchers with useful information if an unexpected pandemic happens so suddenly, like COVID-19. In this work, we present a method to help the retrieval system, the Covrelex-SE system, to provide more high-quality search results. We exploited the power of the large language models (LLMs) to extract the hidden relationships inside the unlabeled publication that cannot be found by the current parsing tools that the system is using. Since then, help the system to have more useful information during retrieval progress.