Generative Artificial Intelligence Transparency in scientific writing: the GAIT 2024 guidance

Abstract

Background: Generative Artificial Intelligence (GAI) tools are increasingly used in research. At present, there is no standardised approach to reporting GAI use. We aimed to produce guidance to support authors in the use of GAI in scientific writing.

Methods: A steering group of academic surgeons with experience in GAI developed draft statements for best practice in reporting GAI use. These statements were refined through iterative discussions using a nominal group technique. A broad network of surgeons and surgical researchers were invited to participate in an online consultation exercise to validate these statements by ranking using a Likert scale. A pre-planned threshold of ≥70% of participants scoring a statement ≥7 would lead to acceptance. Participants were additionally surveyed on the use, opportunities, and risks. Thematic analysis was completed using ChatGPT.

Results: The steering group developed five draft statements, which were validated in the online consultation exercise by 124 participants from 46 countries. Four draft statements were accepted based on this exercise and consolidated into the final Generative AI Transparency (GAIT) guidance: (1) GAI use should be reported in a GAIT statement; (2) GAI use should be mapped using the Contributor Roles Taxonomy; (3) specific prompts used should be reported; (4) authors should retain final responsibility for their work. Example statements to be included in manuscripts include: (1) ChatGPT-4o was used in November 2024 to check and edit statistical code (formal analysis) and edit small sections of the manuscript text for clarity (writing: review & editing). Prompts used are reported in the supplement. The authors should retain final responsibility for their work; (2) No Generative Artificial Intelligence was used to produce, draft, or edit this guidance paper.

Conclusion: The GAIT 2024 guidance will support transparent, structured reporting of the use of generative AI in scientific writing, supporting the integrity of research outputs.