Assessing the Ability of ChatGPT to Screen Articles for Systematic Reviews

Abstract

By organizing knowledge within a research field, Systematic Reviews (SR) provide valuable leads to steer research. Evidence suggests that SRs have become first-class artifacts in software engineering. However, the tedious manual effort associated with the screening phase of SRs renders these studies a costly and error-prone endeavor. While screening has traditionally been considered not amenable to automation, the advent of generative AI-driven chatbots, backed with large language models is set to disrupt the field. In this report, we propose an approach to leverage these novel technological developments for automating the screening of SRs. We assess the consistency, classification performance, and generalizability of ChatGPT in screening articles for SRs and compare these figures with those of traditional classifiers used in SR automation. Our results indicate that ChatGPT is a viable option to automate the SR processes, but requires careful considerations from developers when integrating ChatGPT into their SR tools.

References in corpus (6)

• Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
• A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT
• ChainForge: A Visual Toolkit for Prompt Engineering and LLM Hypothesis Testing
• Instruction Tuning for Large Language Models: A Survey
• Towards Better Chain-of-Thought Prompting Strategies: A Survey
• Automated title and abstract screening for scoping reviews using the GPT-4 Large Language Model

Cited by in corpus (4)

• Streamlining evidence based clinical recommendations with large language models
• Generative Artificial Intelligence for Literature Reviews
• AI Simulation by Digital Twins: Systematic Survey, Reference Framework, and Mapping to a Standardized Architecture
• Goals and Strategies for the Indexing of Publication Types and Study Designs