Generative Artificial Intelligence for Literature Reviews

2026-05-15

AI Summary

Traditional literature reviews struggle with the inefficiency of processing vast volumes of academic texts. This study proposes a novel paradigm that integrates generative artificial intelligence—such as ChatGPT and Elicit—with systematic review methodologies. By employing structured prompt engineering, the approach harnesses large language models’ capabilities in summarization, question answering, information extraction, and multilingual translation, thereby enhancing efficiency while preserving methodological rigor. The work contributes a reusable set of prompting strategies, an analysis of the applicability and limitations of generative AI in literature synthesis, and a practical framework that balances opportunities against potential risks. Furthermore, it invites philosophical reflection on how such technologies may transform the epistemology and practices of scientific knowledge production.

Abstract

Generative artificial intelligence (GenAI), based on large-language models (LLMs), such as ChatGPT, has taken organizations, academia, and the public by storm. In particular, impressive GenAI capabilities such as summarization of large text corpora, question-answering, data extraction, and translation, carry profound implications for the conduct of literature reviews. This impacts science, organizations and the general public, as all can benefit from GenAI-supported literature reviews. Building on the technical foundations of GenAI and grounded in established methodological discourse, this work outlines approaches for conducting literature reviews using both general-purpose (e.g., ChatGPT, Gemini, Claude) and specialized GenAI tools (e.g., Consensus, Elicit). We provide illustrative examples of prompts and suggest methodologically-sound literature review strategies. Throughout this perspective paper, we adopt a balanced approach considering both the opportunities and the risks of relying on GenAI in the conduct of literature reviews. We conclude by discussing philosophical questions related to the effects of GenAI on long-term scientific progress, and also present fruitful opportunities for research on improving the core of GenAI's technology-its architecture and training data-and suggest open issues in GenAI-based literature reviews methodology.

Problem

• Generative Artificial Intelligence
• Literature Reviews
• Large Language Models
• Scientific Methodology
• AI Ethics

Innovation

• Generative Artificial Intelligence
• Literature Review
• Large Language Models
• Methodology
• Prompt Engineering