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

Document Type

Conference Proceeding

Abstract

Systematic reviews (SRs) are pivotal yet time-intensive, often taking over a year to complete due to the vast volume of literature. 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. This paper explores using Generative AI, such as ChatGPT, and external knowledge-augmented information extraction, like Retrieval-Augmented Generation, to enhance SR efficiency. We introduce GEAR-Up, a system that automates query development and translation in SRs. It enriches user queries with additional context from language models and knowledge graphs, facilitating efficient article retrieval from scholarly databases. In collaboration with librarians, our qualitative evaluations show improved reproducibility and quality in search strategies. The demo is available at 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.

APA Citation

Roy, K., Khandelwal, V., Surana, H., Vera, V., Sheth, A., & Heckman, H. (2024). GEAR-Up: Generative AI and external knowledge-based retrieval upgrading scholarly article searches for systematic reviews. Proceedings of the 38th AAAI Conference on Artificial Intelligence.

This document is currently not available here.

Share

COinS