Implementation of Retrieval-Augmented Generation (RAG) in Systematic Reviews: An Approach Applied to Information Assurance in Sustainability
Abstract
Corporate sustainability assurance (CSA) and Corporate Social Responsibility (CSR) disclosures face increasing scrutiny in both academic and professional contexts. However, traditional metadata‐based search engines often fail to capture relevant information hidden in full-text sections. This paper proposes a Retrieval-Augmented Generation (RAG) system that integrates artificial intelligence with a structured indexing approach to enhance systematic literature reviews on sustainability assurance. A corpus of 23 articles was processed, segmenting each paper into labeled sections (e.g., Introduction, Methodology) enriched with metadata. Hybrid semantic indices were built, and specialized RAG agents performed iterative retrieval, improving coverage and reducing omissions caused by keyword-only searches. Results demonstrate that this approach significantly accelerates review time and ensures verifiable, source-linked outputs, promoting deeper analysis of sustainability assurance practices. The multi-agent, modular design further allows extension to other domains and offers a scalable alternative to conventional methods.
How strong is the evidence?
Evidence Hub reads this as a systematic review. Its evidence level is 1 of 5 (Highest · pooled evidence). Pooled evidence from several studies sits at the top of the evidence pyramid.
Read the paper
Related studies
- Knowledge Management Perspective of Generative Artificial Intelligence
- Navigating Generative Artificial Intelligence Promises and Perils for Knowledge and Creative Work
- Characterizing the evolving research on enterprise content management
- Large language models and multimodal foundation models for precision oncology
- From Generative AI to Extended Reality: Multidisciplinary Perspectives on the Challenges, Opportunities, and Future of Educational Computing
- Generative Artificial Intelligence: A New Engine for Advancing Environmental Science and Engineering
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.