Strengths and Weaknesses of ChatGPT Models for Scientific Writing About Medical Vitamin B12: Mixed Methods Study

Abstract

Background ChatGPT is a large language model developed by OpenAI designed to generate human-like responses to prompts. Objective This study aims to evaluate the ability of GPT-4 to generate scientific content and assist in scientific writing using medical vitamin B12 as the topic. Furthermore, the study will compare the performance of GPT-4 to its predecessor, GPT-3.5. Methods The study examined responses from GPT-4 and GPT-3.5 to vitamin B12–related prompts, focusing on their quality and characteristics and comparing them to established scientific literature. Results The results indicated that GPT-4 can potentially streamline scientific writing through its ability to edit language and write abstracts, keywords, and abbreviation lists. However, significant limitations of ChatGPT were revealed, including its inability to identify and address bias, inability to include recent information, lack of transparency, and inclusion of inaccurate information. Additionally, it cannot check for plagiarism or provide proper references. The accuracy of GPT-4’s answers was found to be superior to GPT-3.5. Conclusions ChatGPT can be considered a helpful assistant in the writing process but not a replacement for a scientist’s expertise. Researchers must remain aware of its limitations and use it appropriately. The improvements in consecutive ChatGPT versions suggest the possibility of overcoming some present limitations in the near future.