Abstract
The rapid growth of academic publications has intensified the challenges of conducting rigorous literature reviews, pushing traditional and computational approaches to their limits. While Generative Large Language Models (GLLMs) offer advanced capabilities for summarisation, abstraction, and “synthesis”, their use in scholarly contexts is constrained by hallucination, limited context windows, and weak evidential grounding. Retrieval-Augmented Generation (RAG) mitigates some of these issues by anchoring outputs in verifiable sources, yet current applications remain focused on fact retrieval rather than higher-level conceptual integration. To address this gap, we propose a knowledge graph-based RAG–GLLM approach that combines structured knowledge representation with generative reasoning. Knowledge graphs provide persistent context, reduce hallucination, and enable analysis across five levels of literature review, from concepts to themes. Our research-in-progress outlines the conceptual design, development plan, and early prototyping results, contributing a methodological foundation for scalable, reliable, and theory-informed literature reviews in Information Systems research.
Recommended Citation
Xie, Yancong; Song, Yuanyuan; and Watson, Richard, "A Knowledge Graph-Based RAG-GLLM Approach for Literature
Review and Knowledge Discovery" (2025). ACIS 2025 Proceedings. 37.
https://aisel.aisnet.org/acis2025/37