GEAR-Up: Generative AI and External Knowledge-based Retrieval Upgrading Scholarly Article Searches for Systematic Reviews

TL;DR

This paper introduces GEAR-Up, a system that leverages Generative AI and external knowledge sources to improve the efficiency and accuracy of scholarly article retrieval for systematic reviews.

Contribution

It presents a novel approach combining query expansion with generative AI and knowledge graphs to enhance literature search processes in systematic reviews.

Findings

System effectively enriches search queries with AI and knowledge graphs.

Qualitative evaluation shows improved retrieval accuracy over baseline methods.

Demonstration available online for practical use.

Abstract

Systematic reviews (SRs) - the librarian-assisted literature survey of scholarly articles takes time and requires significant human resources. Given the ever-increasing volume of published studies, applying existing computing and informatics technology can decrease this time and resource burden. Due to the revolutionary advances in (1) Generative AI such as ChatGPT, and (2) External knowledge-augmented information extraction efforts such as Retrieval-Augmented Generation, In this work, we explore the use of techniques from (1) and (2) for SR. We demonstrate a system that takes user queries, performs query expansion to obtain enriched context (includes additional terms and definitions by querying language models and knowledge graphs), and uses this context to search for articles on scholarly databases to retrieve articles. We perform qualitative evaluations of our system through comparison against sentinel (ground truth) articles provided by an in-house librarian. The demo can be found at: https://youtu.be/zMdP56GJ9mU.