Generative Artificial Intelligence for Literature Reviews

TL;DR

This paper explores how generative AI, especially large-language models like ChatGPT, can be used to enhance literature reviews by providing methods, examples, and discussing opportunities and risks.

Contribution

It offers a methodological framework and illustrative prompts for conducting literature reviews with GenAI tools, highlighting both benefits and challenges.

Findings

Illustrative examples of prompts for literature reviews

Methodologically-sound strategies for using GenAI in reviews

Discussion of opportunities, risks, and philosophical implications

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.